© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27618
    Prev
    Next
    INDEX
    Explanations

    quotation" "the" "don" "for" "because"

    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
    panse
    -0.09
     altrett
    -0.08
    gnore
    -0.08
    ouse
    -0.08
    ingleton
    -0.08
     /*!<
    -0.08
    paginator
    -0.08
    urd
    -0.08
    mpeg
    -0.08
    ctrine
    -0.08
    POSITIVE LOGITS
     [
    0.08
     ...
    0.07
     ‘
    0.07
    好åķĬ
    0.07
     [...]
    0.07
     (âĢ¦)
    0.06
    ‘
    0.06
    ä¹ĭä¸ĭ
    0.06
     [âĢ¦]
    0.06
    .").
    0.06
    Activations Density 0.044%

    No Known Activations