© 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. 129982
    Prev
    Next
    INDEX
    Explanations

    code

    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
    licit
    -0.30
    ä¸Ģ件äºĭæĥħ
    -0.26
    (/[
    -0.26
    -hero
    -0.26
    LEMENT
    -0.25
    ongsTo
    -0.25
     *__
    -0.25
    '|
    -0.25
     authorised
    -0.24
    errupt
    -0.24
    POSITIVE LOGITS
    elsen
    0.31
    ockets
    0.28
    人æ°ij
    0.26
    ç³»
    0.25
    etur
    0.24
    磻
    0.24
    NSE
    0.24
     dab
    0.24
     dz
    0.23
    æŀª
    0.23
    Activations Density 14.153%

    No Known Activations