© 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. 26162
    Prev
    Next
    INDEX
    Explanations

    levels and dB

    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
    erator
    -0.09
    åı¯æĥ³
    -0.08
    áĥłáĥĿ
    -0.08
    è¸Ĭ
    -0.08
    otland
    -0.08
    aras
    -0.08
    çĶ
    -0.08
    arder
    -0.08
    åīįä¸ĸ
    -0.07
    æŶéĹ´å®īæİĴ
    -0.07
    POSITIVE LOGITS
     dB
    0.09
    级
    0.08
    dB
    0.08
     attenuation
    0.08
    è¡°åĩı
    0.08
    çŃī级
    0.08
     noise
    0.07
    å¯ĤéĿĻ
    0.07
    -minus
    0.07
     louder
    0.07
    Activations Density 0.020%

    No Known Activations