© 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. 141264
    Prev
    Next
    INDEX
    Explanations

    code, math, 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
    è½½
    -0.27
    quake
    -0.26
    ismatic
    -0.25
    adro
    -0.25
    gmail
    -0.25
    -share
    -0.24
    ERENCE
    -0.24
    èŀºæĹĭ
    -0.24
    Surv
    -0.24
    ãĥIJãĥĥãĤ¯
    -0.24
    POSITIVE LOGITS
     Russ
    0.24
    æĽ³
    0.24
    廳
    0.24
    ding
    0.24
    è´¨éĩıåĴĮ
    0.23
    หมà¸Ķ
    0.23
    çªł
    0.23
    inate
    0.23
     arts
    0.23
    atsu
    0.22
    Activations Density 6.593%

    No Known Activations