© 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. 65009
    Prev
    Next
    INDEX
    Explanations

    type classification

    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
    æľ¬æĸĩçĶ±
    -0.08
    ½ij
    -0.07
    代人
    -0.07
    zyn
    -0.07
    æ£ł
    -0.07
     sinon
    -0.07
    åı¸ç©º
    -0.07
     Sloan
    -0.07
    æĽ´åĬłå¼º
    -0.07
     orgul
    -0.07
    POSITIVE LOGITS
    ç±»åŀĭ为
    0.08
    第ä¸īç§į
    0.08
    ä¸īç±»
    0.07
     type
    0.07
    less
    0.07
     classified
    0.07
    TypeEnum
    0.07
    former
    0.07
    Type
    0.07
    第äºĮç±»
    0.07
    Activations Density 0.241%

    No Known Activations