© 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. 33-TRANSCODER-HP
    7. 53044
    Prev
    Next
    INDEX
    Explanations

    say "Department or punctuation"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ..'
    -0.25
    ÙĪغ
    -0.25
    æİĴè¡Įæ¦ľ
    -0.24
    ap
    -0.24
    etting
    -0.24
    tram
    -0.24
    æ¦ľé¦ĸ
    -0.24
     inter
    -0.24
    ivas
    -0.23
     SHALL
    -0.23
    POSITIVE LOGITS
    ä¸įå¿ĺ
    0.26
     ngũ
    0.24
    DI
    0.24
    cff
    0.24
     cease
    0.24
    hei
    0.24
     Cad
    0.24
     sent
    0.24
     lite
    0.24
    æ°´
    0.24
    Activations Density 0.004%

    No Known Activations