© 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. 18533
    Prev
    Next
    INDEX
    Explanations

    Web pages

    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
    versation
    -0.26
    assage
    -0.26
    ŀæĢ§
    -0.26
     hap
    -0.26
    LICENSE
    -0.26
    çIJĨ
    -0.26
    ied
    -0.25
    æľįåĬ¡ä½ĵç³»
    -0.25
     crossword
    -0.25
    ERVICE
    -0.24
    POSITIVE LOGITS
     garbage
    0.29
     diamonds
    0.28
     Garrett
    0.27
    гал
    0.27
    gars
    0.26
     fishes
    0.26
    andal
    0.26
    glich
    0.26
    ÙĦاØŃظ
    0.26
     foods
    0.25
    Activations Density 0.018%

    No Known Activations