© 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. 63580
    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
    webs
    -0.27
     congr
    -0.26
    wers
    -0.26
    ansi
    -0.26
    vs
    -0.25
    verte
    -0.25
    orses
    -0.24
     ped
    -0.24
     Cobb
    -0.23
    éĿ¢è¯ķ
    -0.23
    POSITIVE LOGITS
    æĢĿæĥ³
    0.28
    tron
    0.27
    omb
    0.26
    ongyang
    0.25
    çīºçī²
    0.25
    à¸īà¸ļ
    0.25
    SSION
    0.25
    _logic
    0.25
    doch
    0.25
    zik
    0.25
    Activations Density 2.154%

    No Known Activations