© 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. 27274
    Prev
    Next
    INDEX
    Explanations

    threshold cutoff point

    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
    адÑĮ
    -0.08
    æĻĤè¨Ī
    -0.07
    åĦŁ
    -0.07
    oreal
    -0.07
    湧
    -0.07
     infos
    -0.07
    ç·ł
    -0.07
    ahlen
    -0.07
     компо
    -0.07
     layouts
    -0.07
    POSITIVE LOGITS
     thresholds
    0.20
     threshold
    0.19
    threshold
    0.18
    éĺĪåĢ¼
    0.18
     Threshold
    0.17
    Threshold
    0.17
    éĹ¨æ§Ľ
    0.15
    éĺĪ
    0.15
    reshold
    0.15
    .threshold
    0.14
    Activations Density 0.052%

    No Known Activations