© 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. 13222
    Prev
    Next
    INDEX
    Explanations

    relate to

    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
    usel
    -0.08
     ford
    -0.07
    çĦ¶å¤§
    -0.07
    بÙĦ
    -0.07
    çªŁ
    -0.07
    渤
    -0.06
    å±ĤéĿ¢
    -0.06
    OMEM
    -0.06
    çĿĢä¸Ģé¢Ĺ
    -0.06
    ÑĢÑıн
    -0.06
    POSITIVE LOGITS
    åľ£æ¯į
    0.07
    OPS
    0.07
    éĹ®å¥½
    0.07
    éĬŃ
    0.07
    -percent
    0.07
    ovar
    0.07
    å§ĵ
    0.07
    她们çļĦ
    0.07
    å¯Įäºİ
    0.07
    nder
    0.07
    Activations Density 0.017%

    No Known Activations