© 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. 43121
    Prev
    Next
    INDEX
    Explanations

    stored data structures

    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
    åĪļéľĢ
    -0.09
    æ¸ī
    -0.08
    æĬĽ
    -0.08
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    æıŃ
    -0.07
    _intent
    -0.07
    åıijéĢģéĤ®ä»¶
    -0.07
    outlined
    -0.07
    Undefined
    -0.07
    .getSimpleName
    -0.07
    POSITIVE LOGITS
     stored
    0.13
     storing
    0.12
     Stored
    0.11
     stores
    0.11
    stored
    0.11
     store
    0.11
    åŃĺåĤ¨åľ¨
    0.10
     ÑħÑĢан
    0.10
    Stored
    0.10
    æĽ´æĸ°çļĦ
    0.10
    Activations Density 0.224%

    No Known Activations