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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98433
    Prev
    Next
    INDEX
    Explanations

    copyright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĮ¿åIJį
    -0.26
    acing
    -0.25
    .tagName
    -0.25
    ACING
    -0.24
    çĻ¼å¸ĥ
    -0.24
     kut
    -0.24
     webpage
    -0.23
    ullo
    -0.23
    wipe
    -0.23
    วา
    -0.23
    POSITIVE LOGITS
    ERGE
    0.25
    omers
    0.25
    éļıæīĭ
    0.24
    aign
    0.24
     consort
    0.24
     fruit
    0.24
    cé
    0.23
    çѵ
    0.23
     Occupation
    0.23
    itel
    0.23
    Activations Density 0.057%

    No Known Activations