© 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. 28272
    Prev
    Next
    INDEX
    Explanations

    not ok or failing

    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
    ernal
    -0.09
    æĹłå®³
    -0.07
    æĹłå¿§
    -0.07
    ä¸Ģå¸Ĩé£İ顺
    -0.07
     integrated
    -0.07
    æĹłå¼Ĥè®®
    -0.07
    ä¾
    -0.07
    abis
    -0.07
     Integrated
    -0.07
     mirac
    -0.07
    POSITIVE LOGITS
     :(
    0.08
    ä¸įçĶĺå¿ĥ
    0.08
    anyi
    0.08
    ä¸įçĶĺ
    0.08
    ä¸įå®ī
    0.08
    ValueChanged
    0.08
     unfavor
    0.08
    å¿ħæľī
    0.07
    ä¸įå®Į
    0.07
    ä¸į符
    0.07
    Activations Density 0.008%

    No Known Activations