© 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. 17900
    Prev
    Next
    INDEX
    Explanations

    scripting separators or separators

    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
    jo
    -0.07
    arani
    -0.06
    pp
    -0.06
    arus
    -0.06
    为æѤ
    -0.06
    aves
    -0.06
    èĥ½ä¿ĥè¿Ľ
    -0.06
    家å®Ŀ
    -0.06
     Ins
    -0.06
     Bean
    -0.06
    POSITIVE LOGITS
    /or
    0.10
    /of
    0.08
    ousel
    0.08
    游åĪĥ
    0.08
    å¸Į
    0.08
    /OR
    0.07
    utan
    0.07
    ä¸īåĪĨ
    0.07
    ä»»ä½ķåħ¶ä»ĸ
    0.07
    åīĬ
    0.07
    Activations Density 0.070%

    No Known Activations