© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43953
    Prev
    Next
    INDEX
    Explanations

    Robert

    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
    ines
    -0.31
    prise
    -0.29
    cha
    -0.28
    cap
    -0.28
    ioned
    -0.26
    èĪĶ
    -0.26
    ero
    -0.26
    Minimal
    -0.25
    jar
    -0.25
    lish
    -0.25
    POSITIVE LOGITS
    è®®
    0.28
    温
    0.26
    -leg
    0.26
    æµģéĢļ
    0.26
    -security
    0.26
    odic
    0.25
    _argument
    0.25
    èĥĮçĿĢ
    0.25
    æ¡Ĩæŀ¶
    0.25
    dict
    0.24
    Activations Density 0.001%

    No Known Activations