© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42403
    Prev
    Next
    INDEX
    Explanations

    cognitive abilities and memory deficits

    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
    è¿Ļç§įåģļæ³ķ
    -0.08
    urator
    -0.07
    adium
    -0.07
     duly
    -0.07
    undler
    -0.07
    èĩªå·±çļĦ身ä½ĵ
    -0.06
    产åĵģæľįåĬ¡
    -0.06
    è¡Įéģĵ
    -0.06
    adero
    -0.06
    gings
    -0.06
    POSITIVE LOGITS
     abilities
    0.14
     ability
    0.12
    æµĭéªĮ
    0.11
     Abilities
    0.11
     tests
    0.11
     skills
    0.10
     deficits
    0.10
     Tests
    0.10
    èĥ½åĬĽ
    0.09
    èĥ½åĬĽçļĦ
    0.09
    Activations Density 0.198%

    No Known Activations