© 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. 7501
    Prev
    Next
    INDEX
    Explanations

    index or children

    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
    stry
    -0.08
    ÑĨен
    -0.08
    继ç»Ńéĺħ读
    -0.07
    èµ·æŃ¢
    -0.07
    æĻĸ
    -0.07
    rées
    -0.07
    ç¿Ĵæħ£
    -0.07
    atatype
    -0.07
     meas
    -0.07
    unders
    -0.07
    POSITIVE LOGITS
    åİŁæľ¬æĺ¯
    0.10
    交æį¢
    0.09
     originally
    0.09
    æľ¬æĿ¥æĺ¯
    0.09
     destined
    0.09
    äºĴæį¢
    0.09
    åİŁæĿ¥
    0.08
    ç½®æį¢
    0.08
     exchange
    0.08
    åİŁæľ¬
    0.08
    Activations Density 0.017%

    No Known Activations