© 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. 13112
    Prev
    Next
    INDEX
    Explanations

    access_token

    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
     forKey
    -0.08
    æ±Łè·¯
    -0.08
    hia
    -0.08
    estia
    -0.08
    对äºİè¿Ļ个
    -0.07
    baka
    -0.07
    SEE
    -0.07
    oenix
    -0.07
    cza
    -0.07
    Ñĩа
    -0.07
    POSITIVE LOGITS
     of
    0.07
    oroz
    0.07
    æĢģ
    0.07
    ure
    0.06
    uteur
    0.06
    atra
    0.06
    ournal
    0.06
    oves
    0.06
    ovic
    0.06
    度
    0.06
    Activations Density 0.020%

    No Known Activations