© 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. 54231
    Prev
    Next
    INDEX
    Explanations

    formal

    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
    enberg
    -0.30
    ullivan
    -0.25
    [email
    -0.24
    egasus
    -0.24
    strconv
    -0.24
    æĸ°ä¸ĸ纪
    -0.23
    ffer
    -0.23
    '][]
    -0.23
    à¹īา
    -0.23
    å¥ĭ
    -0.23
    POSITIVE LOGITS
    lösung
    0.29
     sill
    0.26
     ×Ķ×IJר
    0.26
    oded
    0.26
    ä¹IJ
    0.25
     rejo
    0.25
    eller
    0.25
    body
    0.24
    folk
    0.24
     wording
    0.24
    Activations Density 0.015%

    No Known Activations