© 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. 11287
    Prev
    Next
    INDEX
    Explanations

    probably or maybe

    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
    çĽ¸ä¼ł
    -0.09
    apun
    -0.08
     meanwhile
    -0.08
     patern
    -0.08
    linky
    -0.08
     absolument
    -0.08
    ä»Ģä¹Īåij¢
    -0.07
    algo
    -0.07
    æĥ³å¿ħ
    -0.07
    æį®æĬ¥éģĵ
    -0.07
    POSITIVE LOGITS
    没éĤ£ä¹Ī
    0.08
     subconscious
    0.08
    èĢĮèµ°
    0.08
    èĢ½è¯¯
    0.07
    ä¸į太
    0.07
    ä¸įå¦Ĥ
    0.06
    sense
    0.06
    å°±å¤ŁäºĨ
    0.06
    æĮĩçļĦ
    0.06
     overlooked
    0.06
    Activations Density 0.051%

    No Known Activations