© 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. 12045
    Prev
    Next
    INDEX
    Explanations

    image src attribute

    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
    OTAL
    -0.08
    à¸Ļà¸Ńà¸ĩ
    -0.07
    scientific
    -0.07
    uctor
    -0.07
    udd
    -0.07
    hint
    -0.07
    ors
    -0.07
    iterals
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ìĩł
    -0.07
    POSITIVE LOGITS
    zza
    0.10
    æĮģ
    0.08
    rna
    0.08
    ANÃĩA
    0.07
    enov
    0.07
    _advance
    0.06
    ä¸ĵèIJ¥åºĹ
    0.06
    ä¸½å¨ľ
    0.06
    ÑĥÑī
    0.06
    åĨ¬
    0.06
    Activations Density 0.012%

    No Known Activations