© 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. 20-TRANSCODER-HP
    7. 107295
    Prev
    Next
    INDEX
    Explanations

    Random content and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿĩåı¯
    -0.28
    urry
    -0.27
    ä¸įè§ģäºĨ
    -0.27
    ä½ķå¤Ħ
    -0.27
    /board
    -0.26
    aisy
    -0.26
    éĥ½æĹłæ³ķ
    -0.25
     Lean
    -0.25
    稷
    -0.25
    踱
    -0.25
    POSITIVE LOGITS
     OnPropertyChanged
    0.26
     Hayden
    0.26
     eff
    0.24
    á»ĩn
    0.24
     localized
    0.24
     eve
    0.23
     kost
    0.23
     dak
    0.23
    glyph
    0.23
    .sap
    0.23
    Activations Density 10.349%

    No Known Activations