© 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. 34550
    Prev
    Next
    INDEX
    Explanations

    code examples with explanations

    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
    缮ä¸į
    -0.07
     (
    -0.07
    ↵
    -0.07
    æŶæľī
    -0.06
    æĥŁæľī
    -0.06
     Gat
    -0.06
     sym
    -0.05
    ales
    -0.05
    ared
    -0.05
     form
    -0.05
    POSITIVE LOGITS
    egger
    0.09
    _TODO
    0.08
    ảo
    0.08
     terb
    0.08
    æİ©
    0.08
    гÑĢани
    0.08
     tôt
    0.08
    ETO
    0.08
    tia
    0.08
    iep
    0.08
    Activations Density 0.039%

    No Known Activations