© 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. 63118
    Prev
    Next
    INDEX
    Explanations

    extending, disposed, mounted

    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
    æ®Ĭ
    -0.07
    æ¼ł
    -0.07
     “
    -0.07
    ä¸İå®ŀéĻħ
    -0.06
    μον
    -0.06
     hypothetical
    -0.06
    ä¸İçİ°å®ŀ
    -0.06
     Ble
    -0.06
     generalized
    -0.06
     prä
    -0.06
    POSITIVE LOGITS
    好货
    0.08
    å¼Ģ设æľī
    0.08
    延伸èĩ³
    0.08
    åĪĨåĪ«ä¸İ
    0.08
    aspers
    0.08
    heber
    0.08
    å½ĵå¿ĥ
    0.08
    å®īå¨ľ
    0.08
     extends
    0.08
    extend
    0.08
    Activations Density 0.485%

    No Known Activations