© 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. 88408
    Prev
    Next
    INDEX
    Explanations

    compact

    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
     exc
    -0.29
     Pok
    -0.26
    .flatMap
    -0.26
    dek
    -0.25
    /dr
    -0.24
    Pid
    -0.24
    tlement
    -0.24
     oneself
    -0.24
     tom
    -0.23
    ä½Ĩä¹Ł
    -0.23
    POSITIVE LOGITS
    说åĩº
    0.26
    ино
    0.26
    vero
    0.25
    ivo
    0.24
    ãģ«ãģĹãģ¦
    0.24
    æľīå¤ļå°ij
    0.23
    't
    0.23
    iores
    0.23
    ilee
    0.23
    设æĥ³
    0.23
    Activations Density 0.023%

    No Known Activations