© 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. 4204
    Prev
    Next
    INDEX
    Explanations

    kavanaugh, right leg, adrenal weights

    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
    riv
    -0.07
    rib
    -0.06
    aily
    -0.06
    黼
    -0.06
    auge
    -0.06
    éch
    -0.06
    å¦ĤæŀľæĪij
    -0.06
    çĪ±ä¸Ĭ
    -0.06
    å·²ç»ıç»ĵæĿŁ
    -0.06
    æĭĽ
    -0.06
    POSITIVE LOGITS
    dna
    0.08
    è´´èĨľ
    0.08
     infix
    0.07
    IsActive
    0.07
    idental
    0.07
     accordingly
    0.07
    åħ¬æīĢ
    0.07
     jaoks
    0.07
     désormais
    0.07
    Ascii
    0.07
    Activations Density 0.002%

    No Known Activations