© 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. 88288
    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
     chained
    -0.27
    I
    -0.26
    [
    -0.26
    um
    -0.26
    d
    -0.26
    abo
    -0.25
    ts
    -0.25
    Chain
    -0.25
    积èĵĦ
    -0.25
     tsp
    -0.25
    POSITIVE LOGITS
    rang
    0.29
    empor
    0.28
    idth
    0.27
    comed
    0.27
    cona
    0.24
    ]%
    0.24
    TEGER
    0.24
    ãģ£ãģŁãĤī
    0.24
    gaard
    0.23
    èĢģ人家
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.