© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50144
    Prev
    Next
    INDEX
    Explanations

    lack of or gone

    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
    igram
    -0.07
    strict
    -0.07
    ovin
    -0.07
    Transformation
    -0.06
     strict
    -0.06
    rys
    -0.06
    acam
    -0.06
     arro
    -0.06
     ê°ĢëĵĿ
    -0.06
    gran
    -0.06
    POSITIVE LOGITS
    à¸Ľà¸¥à¹Īà¸Ńยà¹ĥหà¹ī
    0.09
    没äºĨ
    0.09
    没人
    0.09
    没èĥ½
    0.09
    æĶ¾ä»»
    0.08
     lack
    0.08
    失åİ»
    0.08
    æ²Ĵ人
    0.08
    ä»»çĶ±
    0.08
    篮æĿ¿
    0.08
    Activations Density 0.174%

    No Known Activations