© 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. 43163
    Prev
    Next
    INDEX
    Explanations

    closed door

    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
    æĿ¥åĩ½
    -0.07
    alti
    -0.07
    èĦļæīĭæŀ¶
    -0.07
    zec
    -0.07
    åĵŃ声
    -0.07
     revisit
    -0.06
    è¿ĶåĽŀ顶éĥ¨
    -0.06
     getSize
    -0.06
    è¯ĨåŃĹ
    -0.06
    çľ¼è§Ĵ
    -0.06
    POSITIVE LOGITS
     دستÛĮ
    0.08
     Concep
    0.08
    æĪĸ使çĶ¨
    0.07
    æ¡£ä½į
    0.07
     CLOSED
    0.07
     babe
    0.07
    éĢĤéĩı
    0.07
     sele
    0.07
     bewusst
    0.07
    ç´§äºĨ
    0.07
    Activations Density 0.023%

    No Known Activations