© 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. 32-TRANSCODER-HP
    7. 41799
    Prev
    Next
    INDEX
    Explanations

    &

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moduleId
    -0.29
     wedge
    -0.29
    箫
    -0.26
     May
    -0.26
    \Seeder
    -0.24
     ear
    -0.24
    交æİ¥
    -0.24
     cud
    -0.24
    [result
    -0.24
     insertion
    -0.24
    POSITIVE LOGITS
    ãĥ´ãĤ¡
    0.28
    avn
    0.27
    帷
    0.26
     méd
    0.25
    o
    0.25
    cheon
    0.24
    anten
    0.24
    æ³Ľ
    0.24
    ãĤ·ãĥ£ãĥ«
    0.24
    O
    0.24
    Activations Density 0.000%

    No Known Activations