© 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. 107768
    Prev
    Next
    INDEX
    Explanations

    oro

    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
     rin
    -0.29
    _estimators
    -0.25
    -eslint
    -0.25
    æ°¸éģł
    -0.24
    æĢ¿
    -0.24
    /inet
    -0.23
    æľīåIJį
    -0.23
    éķĶ
    -0.23
     Amend
    -0.23
    etype
    -0.23
    POSITIVE LOGITS
     hamm
    0.26
    ase
    0.26
    å²Ļ
    0.25
    aul
    0.25
    ier
    0.24
    ContentSize
    0.24
    ä¹ħ
    0.23
     Hamilton
    0.23
    clud
    0.23
    aves
    0.23
    Activations Density 26.576%

    No Known Activations