Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 60204
    Prev
    Next
    INDEX
    Explanations

    boilerplate from developer docs and source files, especially HTML header/search sections and repeated MIT license comment blocks.

    oai_token-act-pair · gpt-5Triggered 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
     Encore
    -0.07
     fetish
    -0.07
     الدكت
    -0.06
    rack
    -0.06
     (*.
    -0.06
    .fasterxml
    -0.06
    eware
    -0.06
     Selling
    -0.06
    	score
    -0.06
     fool
    -0.06
    POSITIVE LOGITS
    úng
    0.07
    彘
    0.07
    eña
    0.07
     filler
    0.07
    탔
    0.07
     unstable
    0.07
     golden
    0.07
    🐺
    0.07
    長い
    0.07
    -warning
    0.07
    Activations Density 1.996%

    No Known Activations