© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7287
    Prev
    Next
    INDEX
    Explanations

    URLs and colons

    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
     má»ĩnh
    -0.08
    ãĥ«ãĤ¹
    -0.07
    ILLE
    -0.07
    entar
    -0.07
    ardy
    -0.07
    stamp
    -0.07
    regar
    -0.07
    大红
    -0.07
    幽幽
    -0.07
    äºĭä¸ļä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ç±³äºļ
    0.07
    avy
    0.06
    itando
    0.06
     mel
    0.06
    æ³½
    0.06
    haut
    0.06
    yyy
    0.06
     discontin
    0.06
    osto
    0.06
     initial
    0.06
    Activations Density 0.053%

    No Known Activations