© 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. 44816
    Prev
    Next
    INDEX
    Explanations

    topics and specific nouns

    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
    ade
    -0.06
     ill
    -0.06
    —
    -0.06
    Untitled
    -0.06
    aming
    -0.06
    du
    -0.06
    aper
    -0.06
    ader
    -0.05
    .getBytes
    -0.05
    .nodeName
    -0.05
    POSITIVE LOGITS
     Mug
    0.08
    /games
    0.08
    âĸ·
    0.08
    ~~~~~~~~
    0.08
    ãģ¡ãĤĥ
    0.07
     chôm
    0.07
    rauch
    0.07
    ovil
    0.07
    orque
    0.07
    isson
    0.07
    Activations Density 0.072%

    No Known Activations