© 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. 39067
    Prev
    Next
    INDEX
    Explanations

    modify, change, attack, inhibition

    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
     Lap
    -0.08
     lap
    -0.08
    iom
    -0.07
    æļĤè¡Į
    -0.07
    ippi
    -0.07
    åĽ½æĥħ
    -0.07
    occhi
    -0.06
    erv
    -0.06
     Vos
    -0.06
    车
    -0.06
    POSITIVE LOGITS
    缴æݥ影åĵį
    0.12
    缴æݥ影åĵįåĪ°
    0.11
     directly
    0.10
    缴æİ¥è¿Ľåħ¥
    0.10
    缴æİ¥
    0.10
     indirectly
    0.09
    å½±åĵįåĪ°
    0.09
    缴æİ¥æĪĸéĹ´æİ¥
    0.09
    çļĦ缴æİ¥
    0.09
     непоÑģÑĢед
    0.09
    Activations Density 0.206%

    No Known Activations