© 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. 23-TRANSCODER-HP
    7. 24093
    Prev
    Next
    INDEX
    Explanations

    HTML code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ож
    -0.27
    _structure
    -0.26
    arin
    -0.24
    erde
    -0.23
    åľ¨ä¸Ģ个
    -0.23
    yll
    -0.23
    oker
    -0.23
    éľĨ
    -0.23
    ç½Ł
    -0.23
    erry
    -0.23
    POSITIVE LOGITS
     etc
    1.03
    etc
    0.88
    çŃīçŃī
    0.81
    ä¹ĭç±»
    0.63
    ä¹ĭç±»çļĦ
    0.62
    ãģªãģ©
    0.60
    /etc
    0.59
    çŃī
    0.55
    çŃīæĸ¹éĿ¢
    0.55
    çŃīåĨħ容
    0.53
    Activations Density 0.018%

    No Known Activations