© 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. 12-TRANSCODER-HP
    7. 23802
    Prev
    Next
    INDEX
    Explanations

    Dates and time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĪ被
    -0.29
     extensively
    -0.28
    第ä¸Ģ家
    -0.26
     downwards
    -0.26
     extensive
    -0.26
     extreme
    -0.25
    æĺ¯ä¸Ģ家
    -0.25
    çݰ身
    -0.25
     escaped
    -0.25
     Similar
    -0.24
    POSITIVE LOGITS
    对ä»ĸ们
    0.32
    æĩ
    0.31
    让ä»ĸ们
    0.27
    asury
    0.26
    æŁ´
    0.26
    èĹĵ
    0.25
    ectl
    0.25
    pire
    0.24
    ãĥ¡ãĥĩãĤ£
    0.24
    è®ĵä»ĸåĢij
    0.24
    Activations Density 0.001%

    No Known Activations