© 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. 8278
    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
     limiting
    -0.28
    remen
    -0.27
    getDefault
    -0.25
    otch
    -0.25
    .getAs
    -0.25
     mutual
    -0.24
    .getMax
    -0.24
    åĪ¶çº¦
    -0.24
    GetComponent
    -0.24
    getAs
    -0.24
    POSITIVE LOGITS
    éĺ´éĺ³
    0.28
    该游æĪı
    0.27
    被æī§è¡Į
    0.26
    åı£å¤´
    0.25
     niece
    0.25
    éŨå¤ĸ
    0.25
    缮æłĩä»»åĬ¡
    0.25
    hort
    0.25
     incorrectly
    0.25
    èĻ¬
    0.24
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.