© 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. 18929
    Prev
    Next
    INDEX
    Explanations

    `appa`-`B`

    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
    gger
    -0.08
    æĹłåĬŁ
    -0.07
    åĪ©åĻ¨
    -0.07
    utat
    -0.07
    chal
    -0.07
    odin
    -0.07
    æľĢå·®
    -0.07
     Empre
    -0.07
    æķĸ
    -0.07
    okr
    -0.07
    POSITIVE LOGITS
     broadly
    0.07
     joj
    0.07
    èĤļçļ®
    0.07
     напо
    0.07
    è£
    0.06
    ely
    0.06
    éģĩ
    0.06
    avanaugh
    0.06
    väl
    0.06
    èĤ²
    0.06
    Activations Density 0.001%

    No Known Activations