© 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. 57305
    Prev
    Next
    INDEX
    Explanations

    Ca concentration

    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
     canh
    -0.07
    lese
    -0.07
    upert
    -0.06
    ulen
    -0.06
    ãĤ¥
    -0.06
    èī°è¾Ľ
    -0.06
    åĪĨç±»åı·
    -0.06
    nasium
    -0.06
    atee
    -0.06
     deren
    -0.06
    POSITIVE LOGITS
    æ°´
    0.08
    менование
    0.07
    водÑĭ
    0.07
    è°¨
    0.07
    æ°´æĺ¯
    0.07
     водÑĭ
    0.07
    ason
    0.07
    erk
    0.07
    å¸ĥ伦
    0.07
    æĪIJåĵģ
    0.07
    Activations Density 0.002%

    No Known Activations