© 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. 12455
    Prev
    Next
    INDEX
    Explanations

    website embedding or linking

    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
     |:
    -0.07
    plus
    -0.07
     Pon
    -0.07
    ä½ľè¯į
    -0.07
    pon
    -0.07
    rette
    -0.07
     acom
    -0.07
    apl
    -0.06
    anic
    -0.06
     hyp
    -0.06
    POSITIVE LOGITS
    åģ¥
    0.08
    çĶŁçļĦ
    0.07
    .TryParse
    0.07
    _CRYPTO
    0.07
    каÑĥ
    0.07
    лÑĥй
    0.07
    esor
    0.07
    èĢģäºĮ
    0.07
    preso
    0.07
    çļĦä¸Ģæł·
    0.07
    Activations Density 0.195%

    No Known Activations