© 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. 17506
    Prev
    Next
    INDEX
    Explanations

    the sequence of

    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
    aph
    -0.07
    cul
    -0.06
     Bath
    -0.06
    w
    -0.06
     deem
    -0.06
     ãģ§ãģĻãģĮ
    -0.06
    _MULT
    -0.06
    upert
    -0.06
    .ini
    -0.05
    ult
    -0.05
    POSITIVE LOGITS
    stras
    0.08
     непо
    0.08
    ä¸įæľį
    0.08
    ichi
    0.08
    æķĻå¸ĪåĴĮ
    0.07
    ÑģÑĤен
    0.07
    нен
    0.07
    omot
    0.07
    UILD
    0.07
    stype
    0.07
    Activations Density 0.001%

    No Known Activations