© 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. 21329
    Prev
    Next
    INDEX
    Explanations

    rushed or cramming

    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
    ãĥªãĤ¨
    -0.07
    ÏĦÏģο
    -0.06
    ruc
    -0.06
    ÑĤÑĢ
    -0.06
    akh
    -0.06
     Nob
    -0.06
    è¡Ķ
    -0.06
     Argent
    -0.06
     distinctly
    -0.06
    Cog
    -0.06
    POSITIVE LOGITS
    çĽ²çĽ®
    0.12
     blindly
    0.12
    çĽ²çĽ®çļĦ
    0.11
    èĩªä»¥ä¸º
    0.11
    èĥ¡ä¹±
    0.10
    è´¸çĦ¶
    0.10
    rush
    0.10
    è·Łé£İ
    0.10
    è¯ķåĽ¾
    0.10
     rush
    0.10
    Activations Density 0.053%

    No Known Activations