© 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. 130402
    Prev
    Next
    INDEX
    Explanations

    non-natural language text

    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
    RT
    -0.27
    TL
    -0.27
    zym
    -0.26
    PK
    -0.25
    cs
    -0.25
    kol
    -0.24
    ignet
    -0.24
     type
    -0.24
    l
    -0.24
    <decltype
    -0.24
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.29
    %↵↵
    0.28
    åIJį称
    0.28
    bsites
    0.28
    %)↵↵
    0.26
    -shirts
    0.26
    oice
    0.25
    acha
    0.25
    è¿Ļ个éĹ®é¢ĺ
    0.25
    icate
    0.25
    Activations Density 0.073%

    No Known Activations