© 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. 47716
    Prev
    Next
    INDEX
    Explanations

    specific + characteristic/quantity

    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
    ys
    -0.08
    Ø©
    -0.07
     NotImplemented
    -0.07
    shire
    -0.07
    pane
    -0.07
    анда
    -0.07
    ovah
    -0.07
    alie
    -0.07
    sgi
    -0.07
    éĽĨåĽ¢èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    POSITIVE LOGITS
    åħ¶ä»ĸåªĴä½ĵ
    0.08
    åľ¨ä¼Ĺå¤ļ
    0.08
    sorting
    0.07
     riêng
    0.07
    jord
    0.07
    ity
    0.07
    erg
    0.06
    ertia
    0.06
    ordinate
    0.06
    rau
    0.06
    Activations Density 0.007%

    No Known Activations