© 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. 19-TRANSCODER-HP
    7. 7976
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rust
    -0.28
    è·ŁæĪij
    -0.27
    partment
    -0.27
    arser
    -0.27
    usters
    -0.26
    è¶ħè¶Ĭ
    -0.26
    aul
    -0.25
    —or
    -0.25
    åŃº
    -0.25
     exceeding
    -0.25
    POSITIVE LOGITS
    æݨèįIJéĺħ读
    0.26
    perature
    0.25
    çĶŁæ´»è´¨éĩı
    0.25
    .findIndex
    0.24
    _visibility
    0.24
    воз
    0.24
    å¤ĩèĢĥ
    0.24
    æĻĤéĸĵãĤĴ
    0.24
     toned
    0.23
    身价
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.