© 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. 55568
    Prev
    Next
    INDEX
    Explanations

    code blocks and includes

    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
    æĤī
    -0.07
    ilis
    -0.06
    kins
    -0.06
     appunto
    -0.06
    çĥ¦
    -0.06
    inez
    -0.06
    edException
    -0.06
    ipur
    -0.06
    æ±Ŀ
    -0.06
    edy
    -0.06
    POSITIVE LOGITS
    ä¸įå½Ĵ
    0.09
    aturas
    0.07
    ouc
    0.07
    itale
    0.07
    å°ıå±±
    0.07
    utral
    0.07
    zzi
    0.07
    agg
    0.07
     |âĢ¢
    0.07
    æľīåĬ©æĸ¼
    0.06
    Activations Density 0.600%

    No Known Activations