© 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. 28342
    Prev
    Next
    INDEX
    Explanations

    quantization and related words

    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
    hood
    -0.10
    NESS
    -0.09
    pery
    -0.08
    ness
    -0.08
    anness
    -0.08
    itals
    -0.08
    ÑģÑĤеÑĢ
    -0.08
    ading
    -0.08
    ÏĢοÏĦε
    -0.08
    iggs
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    æĢ§åľ°
    0.09
    ãĥ³
    0.09
    enal
    0.08
    å°ĶåŁº
    0.08
    äºĨåľ¨
    0.08
    ifiable
    0.08
    ฯ
    0.08
    äºĨæĪij们
    0.08
    ised
    0.08
    Activations Density 0.026%

    No Known Activations