© 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. 18182
    Prev
    Next
    INDEX
    Explanations

    Japanese

    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
    asty
    -0.28
    bv
    -0.27
    æķĻ
    -0.26
    iap
    -0.25
    apis
    -0.25
    owed
    -0.25
    LV
    -0.24
     LV
    -0.24
    atre
    -0.24
    ä½Ī
    -0.24
    POSITIVE LOGITS
     cal
    0.28
     collective
    0.27
    uros
    0.27
    æľ¨
    0.26
    anka
    0.26
    çĶµåŃIJä¿¡æģ¯
    0.25
     printing
    0.25
    æĹ»
    0.25
    uai
    0.25
    ,ep
    0.25
    Activations Density 1.029%

    No Known Activations