© 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. 19304
    Prev
    Next
    INDEX
    Explanations

    factors of

    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
    Ìģ
    -0.08
     fucked
    -0.08
    -fashioned
    -0.08
    FIXME
    -0.07
    avl
    -0.07
    allas
    -0.07
    kÃŃv
    -0.07
    çļĦåıijå±ķåĴĮ
    -0.07
    pio
    -0.06
    য়
    -0.06
    POSITIVE LOGITS
    ings
    0.12
    ä¹ĭä¸ĢçļĦ
    0.10
    ible
    0.08
    æĢ§çĸ¾çĹħ
    0.08
    ization
    0.08
    able
    0.08
    ãĤ·ãĥĥãĥĹ
    0.08
    stvÃŃ
    0.08
    ount
    0.07
    umin
    0.07
    Activations Density 0.005%

    No Known Activations