© 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. 24476
    Prev
    Next
    INDEX
    Explanations

    HTML head tags

    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
    å½ĵ头
    -0.07
     worst
    -0.06
    vale
    -0.06
    erial
    -0.06
    annes
    -0.06
    ãĤ¿ãĤ¯
    -0.06
    oles
    -0.06
    è·»
    -0.06
    åİī害
    -0.06
     verste
    -0.06
    POSITIVE LOGITS
    uari
    0.08
    åįĥåŃĹ
    0.07
    ieu
    0.07
    [js
    0.07
    æij
    0.07
    incid
    0.07
    [to
    0.07
    EMAT
    0.07
    åľ¨ç¾İ
    0.07
    STATIC
    0.07
    Activations Density 0.001%

    No Known Activations