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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 75759
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
     Invalidate
    -0.07
    رياضي
    -0.07
    metros
    -0.07
    ודי
    -0.07
    ።
    -0.07
    ()).
    -0.07
    anco
    -0.07
    ;"↵
    -0.06
    razione
    -0.06
    dx
    -0.06
    POSITIVE LOGITS
    RE
    0.08
    Folders
    0.07
    下属
    0.07
    (Str
    0.07
     programme
    0.07
     Providing
    0.07
    FR
    0.07
    尕
    0.07
     comed
    0.07
     Beer
    0.07
    Activations Density 0.000%

    No Known Activations