© 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. 107908
    Prev
    Next
    INDEX
    Explanations

    and

    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
    leri
    -0.26
    หร
    -0.25
     Cy
    -0.25
     Bry
    -0.25
    iar
    -0.25
    ç§
    -0.25
    ination
    -0.25
    efined
    -0.24
     Basis
    -0.24
    .populate
    -0.24
    POSITIVE LOGITS
    综åIJĪæ²»çIJĨ
    0.29
    &&!
    0.27
    ãģĵãģ¨ãģ§ãģĻ
    0.26
     rightly
    0.26
     hinge
    0.25
    .iso
    0.25
     discontinued
    0.24
    å¹²èѦ
    0.24
    å±Ĭæ¯ķä¸ļçĶŁ
    0.24
    Inspectable
    0.24
    Activations Density 29.676%

    No Known Activations