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. 19-RESID-POST-AA
    6. 109669
    Prev
    Next
    INDEX
    Explanations

    rc

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    텔
    -0.08
    	Logger
    -0.07
    flt
    -0.07
    膛
    -0.07
    珞
    -0.07
    etten
    -0.07
    骍
    -0.07
    鲴
    -0.07
    oste
    -0.07
    üb
    -0.07
    POSITIVE LOGITS
     proclaim
    0.08
     anyone
    0.07
     speech
    0.07
    _MOD
    0.07
     ASTM
    0.07
     Banking
    0.07
    指数
    0.07
     ritual
    0.07
     rac
    0.07
    等方式
    0.07
    Activations Density 0.007%

    No Known Activations