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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88321
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
     progressives
    -0.08
    ença
    -0.08
     allergy
    -0.07
     pobliżu
    -0.07
     illnesses
    -0.07
    湿润
    -0.07
     atmospheric
    -0.07
     moist
    -0.07
     loosen
    -0.07
    חול
    -0.07
    POSITIVE LOGITS
     aut
    0.07
    abe
    0.07
     nag
    0.07
    ay
    0.07
    ec
    0.07
    互动
    0.07
    .urlopen
    0.07
    /db
    0.07
     BAT
    0.06
    .extra
    0.06
    Activations Density 0.109%

    No Known Activations