© 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. 34321
    Prev
    Next
    INDEX
    Explanations

    components of / elements 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
    swick
    -0.07
    vol
    -0.07
    bie
    -0.07
    ĥĿ
    -0.07
    rink
    -0.07
    νή
    -0.07
    渲
    -0.07
    ehme
    -0.06
    icola
    -0.06
    olics
    -0.06
    POSITIVE LOGITS
     components
    0.14
    è¦ģç´ł
    0.14
     elements
    0.13
    ç»ĦæĪIJéĥ¨åĪĨ
    0.12
     Components
    0.12
    æŀĦæĪIJ
    0.11
    /components
    0.11
    æ§ĭæĪIJ
    0.11
    components
    0.11
    åħĥç´ł
    0.11
    Activations Density 0.106%

    No Known Activations