© 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. 30-TRANSCODER-HP
    7. 96615
    Prev
    Next
    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     really
    -0.90
    really
    -0.75
     Really
    -0.71
     REALLY
    -0.67
    Really
    -0.60
    羣çļĦå¾Ī
    -0.59
     vraiment
    -0.58
     very
    -0.57
    羣çļĦ
    -0.57
    羣çļĦæĺ¯
    -0.53
    POSITIVE LOGITS
    ton
    0.26
    phin
    0.26
    adr
    0.25
    åĵ¥
    0.25
    itech
    0.24
    $b
    0.24
    ÙĬÙĥ
    0.23
    yr
    0.23
     Unix
    0.23
    elia
    0.23
    Activations Density 1.223%

    No Known Activations