© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57217
    Prev
    Next
    INDEX
    Explanations

    structural code and metadata

    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
    -0.07
    æ½®
    -0.07
    åĤį
    -0.07
    (or
    -0.07
    psilon
    -0.07
    estatus
    -0.07
    ее
    -0.06
    åŁ¼
    -0.06
    ult
    -0.06
    ergen
    -0.06
    POSITIVE LOGITS
    çĻ»è®°æīĭç»Ń
    0.07
    ä¸įçĶĺå¿ĥ
    0.07
    uket
    0.07
    ÙģØ´
    0.07
    çļĦè®®æ¡Ī
    0.07
    omi
    0.07
    æĸ°æĿij
    0.07
    ä»Ģä¹ĪåİŁåĽł
    0.07
    æľīä»Ģä¹ĪçĶ¨
    0.07
     pasi
    0.07
    Activations Density 0.001%

    No Known Activations