© 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. 130593
    Prev
    Next
    INDEX
    Explanations

    all

    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
     Whereas
    -0.28
    ately
    -0.27
     Whether
    -0.26
    å®Įæ¯ķ
    -0.25
    corner
    -0.25
    agens
    -0.25
    åIJİéĿ¢
    -0.25
    åŃ©åŃIJ们
    -0.25
    Whether
    -0.24
    OrElse
    -0.24
    POSITIVE LOGITS
    ukt
    0.29
    ",__
    0.27
    isoft
    0.25
     software
    0.25
    éĩĬ
    0.25
    éĩĭ
    0.24
    icot
    0.24
    ·»
    0.24
    iams
    0.24
     itemprop
    0.24
    Activations Density 9.345%

    No Known Activations