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. 59592
    Prev
    Next
    INDEX
    Explanations

    talking to someone

    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
    Registry
    -0.08
     glyph
    -0.07
    amat
    -0.07
     addUser
    -0.07
    ($(".
    -0.06
    izations
    -0.06
     Crack
    -0.06
    $instance
    -0.06
     trust
    -0.06
    рут
    -0.06
    POSITIVE LOGITS
     tale
    0.08
     π
    0.07
    	re
    0.06
     src
    0.06
    攒
    0.06
     ск
    0.06
     мень
    0.06
     völl
    0.06
    	url
    0.06
     kế
    0.06
    Activations Density 0.023%

    No Known Activations