© 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. 29966
    Prev
    Next
    INDEX
    Explanations

    citation markers `[@` and `^[@`

    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
    ivist
    -0.07
    å±±æ¹ĸ
    -0.07
    uban
    -0.07
     gud
    -0.07
    åį±
    -0.06
    ichi
    -0.06
     Scrolls
    -0.06
    odash
    -0.06
    ime
    -0.06
    aph
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¿¡æĪij
    0.07
    èĢģäºĮ
    0.07
    çĴĩ
    0.07
    erias
    0.06
    çĸĻçĺ©
    0.06
    éķ¿ä¹IJ
    0.06
    éľĵ
    0.06
    bson
    0.06
    ר׼
    0.06
    ÑĸÑĢ
    0.06
    Activations Density 0.044%

    No Known Activations