© 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. 33-TRANSCODER-HP
    7. 54137
    Prev
    Next
    INDEX
    Explanations

    companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leading
    -0.38
     leading
    -0.38
    leading
    -0.36
    Leading
    -0.35
    ç¿Ķ
    -0.29
    ä¸Ģæĺ¯
    -0.28
    ä¼ļä¸Ĭ
    -0.28
    åĬŁ
    -0.28
    uen
    -0.26
    çļĦ梦æĥ³
    -0.25
    POSITIVE LOGITS
     such
    0.47
    such
    0.39
     special
    0.39
    special
    0.37
     Special
    0.37
    è¿Ļæł·çļĦ
    0.36
     looking
    0.35
    Special
    0.35
    Such
    0.33
     Such
    0.33
    Activations Density 0.137%

    No Known Activations