© 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. 41532
    Prev
    Next
    INDEX
    Explanations

    instead, with, need

    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
    ä½ĨéļıçĿĢ
    -0.08
    [type
    -0.07
    zeh
    -0.07
    绥
    -0.07
    amos
    -0.06
    aes
    -0.06
    Others
    -0.06
    大æľī
    -0.06
    å°±åĪ«
    -0.06
     dạng
    -0.06
    POSITIVE LOGITS
     instead
    0.11
    æĽ´åĬłæ³¨éĩį
    0.10
    instead
    0.10
     вмеÑģÑĤо
    0.10
     Instead
    0.10
    没æľīéĤ£ä¹Ī
    0.09
     additionally
    0.09
    æĽ´åĬłçļĦ
    0.09
     invece
    0.09
    æĽ´ä¸º
    0.09
    Activations Density 0.250%

    No Known Activations