© 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. 45593
    Prev
    Next
    INDEX
    Explanations

    award-winning class finest skilled

    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
     amo
    -0.07
    Ĺ
    -0.06
    ored
    -0.06
    æĹ©çŁ¥éģĵ
    -0.06
    ilet
    -0.06
     UPDATED
    -0.06
     Corre
    -0.06
    æĵ¦æĭŃ
    -0.06
     rog
    -0.06
    ölker
    -0.06
    POSITIVE LOGITS
    éĻ½åħī
    0.09
    ligh
    0.08
    semble
    0.08
    alas
    0.08
    leys
    0.08
    stech
    0.08
     következ
    0.08
    éĺ³åħī
    0.08
    yai
    0.08
    _conversion
    0.07
    Activations Density 0.001%

    No Known Activations