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. 23-RESID-POST-AA
    6. 246
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atinum
    -0.07
     AMD
    -0.07
     JsonSerializer
    -0.07
     Ko
    -0.07
    ))->
    -0.07
     UPDATED
    -0.07
    utedString
    -0.07
     connected
    -0.07
     ji
    -0.07
    𓃰
    -0.07
    POSITIVE LOGITS
    第三方
    0.07
    .prev
    0.07
    银行卡
    0.07
    fections
    0.06
    	method
    0.06
    햐
    0.06
    .Speed
    0.06
    Vel
    0.06
    -intensive
    0.06
    бл
    0.06
    Activations Density 0.038%

    No Known Activations