© 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. 32424
    Prev
    Next
    INDEX
    Explanations

    code blocks ending

    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
    ÕŃ
    -0.07
    TERS
    -0.07
    æĪijä¸Ģå®ļä¼ļ
    -0.07
    ê³Ħ
    -0.07
    è¦ģåħħåĪĨ
    -0.07
    ิว
    -0.07
    è¦ģä¹Ī
    -0.07
     Genius
    -0.07
    äº¤æľŁ
    -0.06
    å¨ģé£İ
    -0.06
    POSITIVE LOGITS
    ÛĮار
    0.08
    tel
    0.07
    inqu
    0.07
    sen
    0.07
    ston
    0.07
    .quote
    0.07
    éģİäºĨ
    0.07
    iatr
    0.07
    çŁ£
    0.07
    Registered
    0.07
    Activations Density 0.018%

    No Known Activations