© 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. 56850
    Prev
    Next
    INDEX
    Explanations

    ball or projectile motion

    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
    arus
    -0.07
    -elected
    -0.07
    åĬłæ·±
    -0.06
     inteira
    -0.06
    anging
    -0.06
    ihan
    -0.06
     bowed
    -0.06
    æ·±åĮĸ
    -0.06
    rove
    -0.06
    å¹ķåIJİ
    -0.06
    POSITIVE LOGITS
    åĬ¨èĥ½
    0.09
    ital
    0.09
    æĤ¨å½ĵåīįçļĦä½įç½®
    0.09
    lobs
    0.08
    ogna
    0.08
    udad
    0.08
    estin
    0.08
    åĪĿå§ĭ
    0.08
    unds
    0.08
    éĩıåĬĽ
    0.08
    Activations Density 0.007%

    No Known Activations