© 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. 31-TRANSCODER-HP
    7. 18941
    Prev
    Next
    INDEX
    Explanations

    diary/code/diagnostics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seven
    -0.28
    avings
    -0.28
    té
    -0.27
    formation
    -0.26
     seven
    -0.26
    comb
    -0.26
    castle
    -0.25
     inv
    -0.25
    ä¸ĥ个
    -0.25
    apesh
    -0.25
    POSITIVE LOGITS
    åĴ¬
    0.27
     Whitney
    0.27
    è¡Į为
    0.26
     Welfare
    0.26
    pline
    0.26
    ãĤĦãĤī
    0.26
    åİĤ
    0.26
    atri
    0.25
    emacs
    0.25
    åĿIJ
    0.24
    Activations Density 0.098%

    No Known Activations