© 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. 57898
    Prev
    Next
    INDEX
    Explanations

    not seen since

    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
    ä¸įèĥ½è®©
    -0.08
    combe
    -0.08
    ×ķ×ķת
    -0.07
    ä½Ĩä¸įèĥ½
    -0.07
    okka
    -0.07
     μην
    -0.07
    гова
    -0.07
    éĵĽ
    -0.07
    ä¸įèĥ½æľī
    -0.07
    æĹ¥åĪ¶
    -0.07
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
     سÙĪÙī
    0.10
     sequer
    0.10
     anymore
    0.10
     any
    0.09
     anything
    0.09
    çļĦä»»ä½ķ
    0.09
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.09
    any
    0.09
     siquiera
    0.09
    Activations Density 0.786%

    No Known Activations