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. 333
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
    _stdio
    -0.07
    .setMinimum
    -0.07
     mock
    -0.07
    otypical
    -0.07
    _entry
    -0.07
    濠
    -0.07
    痕
    -0.07
    סכם
    -0.06
     актив
    -0.06
    ")));↵
    -0.06
    POSITIVE LOGITS
    いろんな
    0.07
    -base
    0.07
    <{
    0.06
     Json
    0.06
    天府
    0.06
    _else
    0.06
     Of
    0.06
    /nav
    0.06
    fg
    0.06
     flora
    0.06
    Activations Density 0.081%

    No Known Activations