© 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. 40618
    Prev
    Next
    INDEX
    Explanations

    detection limits and measurement parameters

    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
    æĸĽ
    -0.07
     separated
    -0.07
    å¾ħ
    -0.07
    omb
    -0.07
    /internal
    -0.06
    builtin
    -0.06
    亲
    -0.06
    èĥĸ
    -0.06
    å¢ĥ
    -0.06
    好åIJĹ
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī为
    0.09
    Official
    0.08
    çķĮå®ļ
    0.08
    umbre
    0.08
    _definition
    0.08
     unofficial
    0.08
    ULER
    0.08
    defined
    0.08
    -definition
    0.08
    riterion
    0.08
    Activations Density 0.092%

    No Known Activations