© 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. 21686
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    Porno
    -0.08
    å°Ķå¤ļ
    -0.08
    OffsetTable
    -0.08
    ValueCollection
    -0.07
    BitFields
    -0.07
    ä¸´æ±Ł
    -0.07
    YRO
    -0.07
     Gabin
    -0.07
    OptionsResolver
    -0.07
    常èŃĺ
    -0.07
    POSITIVE LOGITS
    antaran
    0.07
    rack
    0.06
    Ïįν
    0.06
    ivel
    0.06
    Ĺ
    0.06
    aland
    0.06
     tal
    0.06
     tas
    0.06
     asc
    0.06
    æ·±åľ³è¯ģåĪ¸äº¤æĺĵæīĢ
    0.06
    Activations Density 0.042%

    No Known Activations