© 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. 98263
    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
    举
    -0.30
    宵
    -0.27
    ç´¯
    -0.26
    lfw
    -0.26
    Ĵ
    -0.25
    angen
    -0.25
    bben
    -0.24
    country
    -0.24
    eba
    -0.24
     country
    -0.24
    POSITIVE LOGITS
    umps
    0.24
     flashes
    0.24
    $pdf
    0.23
    åĨ²åĩ»
    0.22
     Child
    0.22
    /ubuntu
    0.22
     sweeps
    0.22
    spirit
    0.22
     incor
    0.22
    stick
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.