© 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. 89551
    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
    å¼Ģåħ³
    -0.27
    ç»
    -0.27
    åĪĨæł¡
    -0.27
    åĨĴ
    -0.25
     ÑĢежим
    -0.24
    åĢĭ
    -0.24
    åĵªä¸ª
    -0.23
    éĺ¶
    -0.23
    åĴ½åĸī
    -0.23
    Thickness
    -0.23
    POSITIVE LOGITS
    izedName
    0.29
     legalized
    0.28
    mast
    0.25
     NIL
    0.24
    æľĢ常è§ģçļĦ
    0.24
    àºļ
    0.24
     Municip
    0.24
    ä¸į解
    0.24
    DOT
    0.24
    ä¸įè¿ľ
    0.24
    Activations Density 0.270%

    No Known Activations

    This feature has no known activations.