© 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. 18486
    Prev
    Next
    INDEX
    Explanations

    Ul

    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
    ancy
    -0.27
     ph
    -0.26
    áµIJ
    -0.26
     mes
    -0.25
     flats
    -0.25
     mens
    -0.25
     tụ
    -0.24
    á»ĩt
    -0.24
     heter
    -0.24
    å¼Ĥ
    -0.24
    POSITIVE LOGITS
    irs
    0.31
    iar
    0.28
    íĬ¸
    0.25
    .getRaw
    0.25
    饱åĴĮ
    0.25
    IRON
    0.24
    uja
    0.24
    èµ°å»Ĭ
    0.24
    æij©æĵ¦
    0.24
    éĢ¢
    0.24
    Activations Density 0.039%

    No Known Activations