© 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. 43649
    Prev
    Next
    INDEX
    Explanations

    let

    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
    çĥĤ
    -0.29
    çī¹äº§
    -0.24
    out
    -0.24
    onces
    -0.24
    NA
    -0.24
    fdb
    -0.24
    Void
    -0.24
    æĬĬ
    -0.24
    å¢Ł
    -0.24
    èĥĮçĿĢ
    -0.23
    POSITIVE LOGITS
    Õļ
    0.37
    &apos
    0.35
    `s
    0.33
    ÂĴ
    0.33
    âĤ¬âĦ¢
    0.32
    ʼ
    0.31
    ’s
    0.30
    ´s
    0.30
    'av
    0.30
    ’
    0.30
    Activations Density 0.008%

    No Known Activations