© 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. 46009
    Prev
    Next
    INDEX
    Explanations

    scores and confidence thresholds

    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
    Blo
    -0.08
    гÑĥÑĢ
    -0.08
    å¿ĥå¿ĥ
    -0.08
    arters
    -0.07
    кÑĤи
    -0.07
    Äįas
    -0.07
     Chatt
    -0.07
     Zun
    -0.07
    æĪĸå°ij
    -0.07
     Volunt
    -0.06
    POSITIVE LOGITS
     scores
    0.11
     score
    0.10
    -score
    0.09
     Scores
    0.09
     thresholds
    0.09
     confidence
    0.08
    -confidence
    0.08
     threshold
    0.08
     Score
    0.08
    likelihood
    0.08
    Activations Density 0.034%

    No Known Activations