© 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. 44208
    Prev
    Next
    INDEX
    Explanations

    own collection/home/unit

    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
     skall
    -0.07
    使æĪij
    -0.07
    èĩªå·²
    -0.07
    !!!!!!!!
    -0.07
    åıĹéªĹ
    -0.07
    ----------------------------------------------------------------
    -0.07
    å¹´éĿĴ
    -0.07
    éĢģæĪij
    -0.07
    !!!!!
    -0.06
    女çļĦ
    -0.06
    POSITIVE LOGITS
    Âł
    0.12
    0.11
     [âĢ¦]
    0.11
     downright
    0.10
    –and
    0.10
    0.10
     bezieh
    0.09
     –**
    0.09
     —
    0.09
    ligh
    0.09
    Activations Density 1.106%

    No Known Activations