© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 129443
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    phrases and tokens found in forum UI and post metadata (usernames, dates, post counts, links, "Share"/"Link" buttons).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    我们都
    -0.08
     возд
    -0.07
    :start
    -0.07
    不知
    -0.06
    ‰
    -0.06
    了一会儿
    -0.06
    穷
    -0.06
     perg
    -0.06
    WhatsApp
    -0.06
    (".
    -0.06
    POSITIVE LOGITS
     favorites
    0.07
     sulfate
    0.07
    anti
    0.07
    玩法
    0.07
    وي
    0.07
    olic
    0.07
    	T
    0.07
     honorable
    0.07
    شكل
    0.06
     HOL
    0.06
    Activations Density 0.084%

    No Known Activations