© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13356
    Prev
    Next
    INDEX
    Explanations

    combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ŀäºij
    -0.07
     emb
    -0.06
    åħ¨åĽ½ç»Łä¸Ģ
    -0.06
    åĪĨæ°´
    -0.06
    lier
    -0.06
    stek
    -0.06
    _BAL
    -0.06
     est
    -0.06
    åķ¼
    -0.06
     dem
    -0.06
    POSITIVE LOGITS
     combinations
    0.18
    ç»ĦåIJĪ
    0.14
     combos
    0.14
     combina
    0.13
     permutations
    0.13
     комбина
    0.13
    binations
    0.12
    çļĦç»ĦåIJĪ
    0.12
     Combination
    0.12
    _comb
    0.11
    Activations Density 0.055%

    No Known Activations