© 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. 11-RESID-POST-AA
    11. 92880
    Prev
    Next
    INDEX
    Explanations

    Licensed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whatsoever
    -0.06
     makeup
    -0.06
    “She
    -0.06
     adorned
    -0.06
    の方
    -0.06
     Insight
    -0.06
    Subscription
    -0.06
     Enlightenment
    -0.06
     imposing
    -0.06
     maximize
    -0.06
    POSITIVE LOGITS
    Streamer
    0.08
    _hello
    0.07
     redirect
    0.07
    尼亚
    0.07
    DataURL
    0.07
    哈尔
    0.07
    _bundle
    0.07
     다시
    0.07
     struggles
    0.07
    危险
    0.07
    Activations Density 0.003%

    No Known Activations