© 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. 22455
    Prev
    Next
    INDEX
    Explanations

    real

    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
    åĪĨ级
    -0.26
    Grade
    -0.26
     qint
    -0.25
    mino
    -0.25
     Briggs
    -0.25
    stown
    -0.25
    è´Łè´£
    -0.24
    表示
    -0.24
    æĴŀ
    -0.24
    bject
    -0.24
    POSITIVE LOGITS
    èĪª
    0.28
    ãĤ¢ãĤ¤
    0.26
    à¹Ħà¸Ń
    0.26
    Ä°LÄ°
    0.26
    ADVERTISEMENT
    0.25
    ||(
    0.25
    å±ıéļľ
    0.25
     Aren
    0.24
    æĦıè§ģ建议
    0.24
    ugen
    0.24
    Activations Density 0.003%

    No Known Activations