© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13928
    Prev
    Next
    INDEX
    Explanations

    .js, .wrap, .code, .msg

    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
    enje
    -0.07
    æĿ°ä½ľ
    -0.06
    åĢ©
    -0.06
    ents
    -0.06
    æį·
    -0.06
    çŁ¢
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    ce
    -0.06
    enser
    -0.06
    åľ¨åľ°
    -0.06
    POSITIVE LOGITS
    elos
    0.07
     forg
    0.07
    akang
    0.07
    ró
    0.07
    çĤºä¸»
    0.07
    à¹Īาย
    0.07
     millenn
    0.07
     Seam
    0.07
    ảo
    0.07
    _cats
    0.07
    Activations Density 0.269%

    No Known Activations