© 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. 18-TRANSCODER-HP
    7. 88628
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åģĩ
    -0.30
    orton
    -0.26
    çģĮ
    -0.26
    &E
    -0.26
    æĥ³è±¡
    -0.25
    ;element
    -0.25
    oor
    -0.24
     &$
    -0.24
    说è¯Ŀ
    -0.24
     reuse
    -0.24
    POSITIVE LOGITS
    åį§å®¤
    0.28
    å¥ĹæĪ¿
    0.25
    ICY
    0.25
     <<=
    0.24
    ApiClient
    0.24
     //=
    0.24
    ä¸ĭè¡Į
    0.24
    setTitle
    0.24
    imony
    0.23
    éĶħ
    0.23
    Activations Density 2.026%

    No Known Activations

    This feature has no known activations.