© 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. 17168
    Prev
    Next
    INDEX
    Explanations

    sharper, displacement, adjustment

    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
    ç¡®æľī
    -0.07
    èİ·å¾ĹåĽ½å®¶
    -0.07
    rake
    -0.07
     Rec
    -0.06
    æĥĬ人
    -0.06
    çªģ
    -0.06
    æĸ°æŧ
    -0.06
     Ponta
    -0.06
    çªģèµ·
    -0.06
    æī¦
    -0.06
    POSITIVE LOGITS
    è°ĥæķ´
    0.10
    è¿Ľè¡Įè°ĥæķ´
    0.09
    è°ĥåīĤ
    0.09
    åĴĮè°ĥæķ´
    0.09
     adjusting
    0.09
     Adjust
    0.09
    è°ĥæķ´çļĦ
    0.09
     adjustment
    0.08
    åıįé¦Ī
    0.08
    åģıåIJij
    0.08
    Activations Density 0.017%

    No Known Activations