© 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. 112407
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     <![
    -0.29
    back
    -0.25
    LV
    -0.25
    èĥĮ
    -0.25
    çijĽ
    -0.24
    backs
    -0.23
    <class
    -0.23
    speed
    -0.23
    calculator
    -0.23
    pmat
    -0.23
    POSITIVE LOGITS
    inho
    0.27
    acket
    0.27
    æĥłæ°ij
    0.25
    *)"
    0.25
    undo
    0.24
    ķĮ
    0.24
    ('('
    0.24
    饥饿
    0.23
    amped
    0.23
    对æīĭ
    0.22
    Activations Density 0.030%

    No Known Activations

    This feature has no known activations.