© 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. 87478
    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
    atern
    -0.27
     authentic
    -0.25
    builtin
    -0.24
    _phy
    -0.24
    ward
    -0.24
     fibre
    -0.23
     attached
    -0.23
     equal
    -0.23
    åĪĿä¸ī
    -0.23
     disag
    -0.23
    POSITIVE LOGITS
    HING
    0.27
    masked
    0.26
    æľīæĽ´å¥½çļĦ
    0.26
    кÑĢи
    0.24
    ãĥ¬ãĥ¼ãĤ·ãĥ§ãĥ³
    0.24
    .Promise
    0.24
     lamb
    0.24
    (NS
    0.23
    éĿĻéĿĻåľ°
    0.23
    ⼦
    0.23
    Activations Density 0.069%

    No Known Activations

    This feature has no known activations.