© 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. 98778
    Prev
    Next
    INDEX
    Explanations

    Citations and legal documents

    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
    ffer
    -0.28
     convincing
    -0.26
    fer
    -0.26
    iful
    -0.26
    usage
    -0.25
    bia
    -0.25
    ître
    -0.25
    .usage
    -0.25
    \Repositories
    -0.25
     Ske
    -0.24
    POSITIVE LOGITS
     Modi
    0.28
    è´¸
    0.27
    :///
    0.24
    ificio
    0.24
    åı¦ä¸Ģç§į
    0.23
     puff
    0.23
    è°ĵ
    0.23
    /****************************************************************************
    0.23
    çľ¼çľĭ
    0.23
     tắt
    0.23
    Activations Density 0.014%

    No Known Activations