© 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. 44092
    Prev
    Next
    INDEX
    Explanations

    item c

    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
    缸åħ³éĹ®çŃĶ
    -0.07
    orsi
    -0.07
    entiel
    -0.07
    ä¸İ人
    -0.07
    enet
    -0.07
    åħ®
    -0.07
    å®ļçĤ¹
    -0.07
    å§Ĩæĸ¯
    -0.06
    é«ĺ级ä¸ŃåѦ
    -0.06
    strand
    -0.06
    POSITIVE LOGITS
    æľªè¢«
    0.10
    åī©ä¸ĭçļĦ
    0.10
    åī©
    0.09
     remaining
    0.09
    åī©ä½Ļ
    0.09
    没æľī被
    0.08
    çŃīéĿŀ
    0.08
     übrig
    0.08
    æ¡ijæĭ¿
    0.08
    IDEO
    0.08
    Activations Density 0.018%

    No Known Activations