© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    scenario, scenario, consideration, reason

    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
    ide
    -0.07
    罡
    -0.06
    ç»į
    -0.06
    éģ¨
    -0.06
    .mo
    -0.06
    IDGET
    -0.06
    æľī幸
    -0.06
    ç²¹
    -0.06
    nbr
    -0.06
    sst
    -0.06
    POSITIVE LOGITS
    åĢĴéĢ¼
    0.12
    ä¿ĥ使
    0.10
    è¦ģæ±Ĥè¿Ľè¡Į
    0.09
    .require
    0.09
    è¦ģæ±Ĥåľ¨
    0.09
    è¦ģæ±Ĥ
    0.09
    åıĬæŶè°ĥæķ´
    0.09
    æĺİç¡®è¦ģæ±Ĥ
    0.09
    åĤ¬çĶŁ
    0.09
    迫使
    0.09
    Activations Density 0.202%

    No Known Activations