© 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. 24273
    Prev
    Next
    INDEX
    Explanations

    formula, math, code, header

    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
    βα
    -0.08
    ...*
    -0.07
    ubo
    -0.07
    以åıĬå¦Ĥä½ķ
    -0.07
    è±ļ
    -0.07
     (**
    -0.07
    å¼Ģ头çļĦ
    -0.07
    âĢ¦the
    -0.07
    __*/
    -0.07
    å¦Ĥä½ķ解åĨ³
    -0.07
    POSITIVE LOGITS
    .datab
    0.07
    atge
    0.07
     =
    0.07
    \:
    0.06
    é«ĺåħ´åħ´
    0.06
    ãĤµãĤ¤ãĥ³
    0.06
    稽
    0.06
    ,proto
    0.06
    еÑĩи
    0.06
     ::=
    0.06
    Activations Density 0.008%

    No Known Activations