© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    enter and type

    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
    andra
    -0.08
    ÑĢен
    -0.07
    amac
    -0.06
    ÅĻe
    -0.06
    å±Ģåľ°
    -0.06
    好äºĭ
    -0.06
    aksa
    -0.06
    اÙĩ
    -0.06
    .tools
    -0.06
    lice
    -0.06
    POSITIVE LOGITS
    è¿Ľåİ»
    0.10
    å®Įæ¯ķ
    0.09
    å®Įæ¯ķåIJİ
    0.08
    è¾ĵåħ¥
    0.08
    æŃ£ç¡®çļĦ
    0.08
    åĩĨç¡®çļĦ
    0.08
    ukkan
    0.08
    prising
    0.08
    åĴĮåĪĨæŀIJ
    0.08
    ëĦ£
    0.08
    Activations Density 0.125%

    No Known Activations