© 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. 1399
    Prev
    Next
    INDEX
    Explanations

    so followed by words

    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
    resenter
    -0.09
    orrent
    -0.08
    æĸ°åĬłåĿ¡
    -0.07
    æīĢ以è¦ģ
    -0.07
    åĽłä¸ºæĪij
    -0.07
    èĩªå·±è¦ģ
    -0.07
    urrent
    -0.07
    Å¡in
    -0.07
    bens
    -0.07
     '*',
    -0.07
    POSITIVE LOGITS
     it
    0.07
    ÙĦÙħ
    0.07
    è¿ľè¿ij
    0.07
    ilt
    0.06
    éĽĨåĽ¢èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.06
    åħįä¸įäºĨ
    0.06
    itm
    0.06
    è¿ľå¤§
    0.06
    iled
    0.06
    éĤ£è¾¹
    0.06
    Activations Density 0.069%

    No Known Activations