© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    all sorts of, much less, some 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
     Everywhere
    -0.07
    缺çĤ¹æĺ¯
    -0.07
    Ñħан
    -0.07
    çĺ¾
    -0.07
    ä½ķå¿ħ
    -0.06
    _patches
    -0.06
    atoires
    -0.06
    åݿ人
    -0.06
    riors
    -0.06
    ìļ´ëį°
    -0.06
    POSITIVE LOGITS
     kinds
    0.08
    åĽŃè·¯
    0.08
     sorts
    0.08
    ç´ļ
    0.07
     particular
    0.07
     sembl
    0.07
    个æĪĸå¤ļ个
    0.07
    agl
    0.06
    大çIJĨ
    0.06
    iin
    0.06
    Activations Density 1.266%

    No Known Activations