© 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. 130407
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    WISE
    -0.31
    ally
    -0.26
     mobile
    -0.25
    adel
    -0.24
     Mobile
    -0.24
    etch
    -0.24
    ologia
    -0.24
    ensive
    -0.23
    guard
    -0.23
    移åĬ¨
    -0.23
    POSITIVE LOGITS
     porter
    0.27
    ðŁijĭ
    0.27
    uster
    0.26
    åĴĮå®ĮåĸĦ
    0.25
    è¿Ń
    0.25
    ë¹ħ
    0.25
     Verified
    0.25
    ç»Ī身
    0.25
     mediocre
    0.25
    USTER
    0.24
    Activations Density 8.267%

    No Known Activations