© 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. 3106
    Prev
    Next
    INDEX
    Explanations

    interested in

    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
     bursting
    -0.07
    -
    -0.06
    ammel
    -0.06
    äºļå½ĵ
    -0.06
    .dm
    -0.06
    .times
    -0.06
    èijĹ
    -0.06
    1
    -0.06
     dm
    -0.06
    .
    -0.06
    POSITIVE LOGITS
     funcs
    0.09
    lest
    0.08
    etje
    0.08
    è¸ıè¸ıå®ŀ
    0.08
    hti
    0.08
    æīĢèĥ½åıĬ
    0.08
    IPPING
    0.07
    ä¸įè¿ĩäºĨ
    0.07
    çons
    0.07
    æŀģäºĨ
    0.07
    Activations Density 0.006%

    No Known Activations