© 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. 111452
    Prev
    Next
    INDEX
    Explanations

    technical/medical articles

    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
    /apache
    -0.31
     behold
    -0.29
    碰æĴŀ
    -0.28
    è®´
    -0.26
     challeng
    -0.26
     blossom
    -0.25
     courtesy
    -0.25
     disap
    -0.25
     powers
    -0.25
    aģı
    -0.24
    POSITIVE LOGITS
    atile
    0.30
    iples
    0.29
    (AT
    0.27
    esting
    0.26
    ifter
    0.24
    MMM
    0.24
     CommandType
    0.24
    VML
    0.24
    жи
    0.23
    iele
    0.23
    Activations Density 0.108%

    No Known Activations