© 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. 23152
    Prev
    Next
    INDEX
    Explanations

    $\xrightarrow{P}$ or "$X$" followed by punctuation

    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
    ity
    -0.07
    onso
    -0.07
    enstein
    -0.07
    åĴĮäºĮ
    -0.07
    ers
    -0.07
    ekyll
    -0.07
    erre
    -0.07
    èĪªç©ºèĪªå¤©å¤§åѦ
    -0.07
    erin
    -0.07
    errupt
    -0.07
    POSITIVE LOGITS
    riqu
    0.09
    sto
    0.08
    eto
    0.08
    оваÑĤелÑĮно
    0.08
    riel
    0.08
    _DIAG
    0.08
    ÛĮ
    0.07
    ynchronously
    0.07
    lifi
    0.07
    odia
    0.07
    Activations Density 0.002%

    No Known Activations