© 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. 41526
    Prev
    Next
    INDEX
    Explanations

    negotiation, control, shopping, data, perceived

    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
    estra
    -0.08
    è°Ĭ
    -0.07
    åIJĦæĸ¹éĿ¢
    -0.07
    elok
    -0.07
    ripper
    -0.07
    æĶ¿æ²»ä¸Ĭ
    -0.07
    ç¨Ģ
    -0.06
    rik
    -0.06
    quilla
    -0.06
    istry
    -0.06
    POSITIVE LOGITS
     cross
    0.09
     fr
    0.08
    Fr
    0.07
     reverse
    0.07
    交äºĴå¼ı
    0.07
    obox
    0.07
    Reverse
    0.07
    éĢĨåIJij
    0.07
     bif
    0.07
    YO
    0.07
    Activations Density 0.057%

    No Known Activations