© 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. 45880
    Prev
    Next
    INDEX
    Explanations

    versus or comparing values

    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
    =cut
    -0.08
    hä
    -0.07
    graf
    -0.06
    urio
    -0.06
    RODUCTION
    -0.06
    è¿ľç¦»
    -0.06
    éľŀ
    -0.06
    大æ¦Ĥ
    -0.06
    èĶ½
    -0.06
    hum
    -0.06
    POSITIVE LOGITS
     vs
    0.09
     versus
    0.08
    _CMP
    0.08
    æ¥Ĥ
    0.08
     comparing
    0.08
    .mk
    0.08
     comparisons
    0.08
     compara
    0.08
    enang
    0.08
    obia
    0.08
    Activations Density 0.009%

    No Known Activations