© 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. 31047
    Prev
    Next
    INDEX
    Explanations

    people with surnames ending in -er, -ran, -ling, or names starting with Nog, Nak, McC, Ros

    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
    çĮľ
    -0.07
     Aé
    -0.07
    $',
    -0.06
    åIJĪå½±
    -0.06
    ä¸įç»ı
    -0.06
    æµ·æ°´
    -0.06
    æ²¢
    -0.06
    .library
    -0.06
     prov
    -0.06
    fst
    -0.06
    POSITIVE LOGITS
    macher
    0.09
    ä»İåħ¶
    0.08
    nos
    0.07
    å©·
    0.07
    insic
    0.07
    åĬłåħ³æ³¨
    0.07
    mira
    0.07
    åľ¨åħ¶
    0.07
    acte
    0.07
    饱
    0.07
    Activations Density 0.066%

    No Known Activations