© 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. 23-TRANSCODER-HP
    7. 24461
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿İ
    -0.31
     innings
    -0.26
    .”
    -0.25
    aga
    -0.24
    Fl
    -0.24
     calmly
    -0.24
    еÑĢе
    -0.24
     QList
    -0.23
    Flight
    -0.23
    对åŃ©åŃIJ
    -0.23
    POSITIVE LOGITS
    åıĹçĽĬ
    0.36
    indy
    0.33
    .TryParse
    0.32
    achable
    0.30
    第ä¸ī次
    0.28
    PathVariable
    0.28
    orre
    0.26
    -employed
    0.26
    ached
    0.25
    orm
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.