© 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. 32-TRANSCODER-HP
    7. 43731
    Prev
    Next
    INDEX
    Explanations

    rates and levels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ypress
    -0.26
    DisplayStyle
    -0.26
    signup
    -0.25
    .GetData
    -0.24
    è¿ŁåĪ°
    -0.24
    /forms
    -0.24
    çķĻè¨ĢæĿ¿
    -0.24
    éĩįè¦ģåĽłç´ł
    -0.24
    blade
    -0.24
    _forms
    -0.23
    POSITIVE LOGITS
     tune
    0.62
     rate
    0.40
    çİĩ
    0.37
     tuning
    0.35
     razón
    0.33
     speed
    0.33
     level
    0.32
     tunes
    0.31
    éĢŁåº¦
    0.31
     ratio
    0.31
    Activations Density 0.003%

    No Known Activations