© 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. 23484
    Prev
    Next
    INDEX
    Explanations

    JSON objects and structure types

    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
    erg
    -0.08
    ond
    -0.07
    uzzi
    -0.06
    (
    -0.06
    _ATTRIBUTES
    -0.06
    oord
    -0.06
    ä¸Ģéĺµ
    -0.06
    ä¸Ģç³»åĪĹ
    -0.06
    us
    -0.06
    çĩķ
    -0.06
    POSITIVE LOGITS
    å±ij
    0.08
    æĪijåIJ§
    0.08
    mites
    0.08
    ROME
    0.08
    FileType
    0.08
    ξε
    0.08
    Äįe
    0.08
    ImageUrl
    0.08
    æĸĩåĵ²
    0.07
    rome
    0.07
    Activations Density 0.013%

    No Known Activations