© 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. 28628
    Prev
    Next
    INDEX
    Explanations

    separation, distance, similarity, delta

    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
     Bota
    -0.08
    ambo
    -0.08
    eschi
    -0.08
    ä¸īæĸ¹
    -0.08
    ndef
    -0.08
    uline
    -0.07
    Ĩł
    -0.07
    oria
    -0.07
    .cmd
    -0.07
    .modal
    -0.07
    POSITIVE LOGITS
    åIJĮè¡ĮçļĦ
    0.10
    缸éĤ»
    0.09
    åIJĮè¡Į
    0.09
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.09
    人ä¸İ人ä¹ĭéĹ´
    0.09
    人ä¸İ人
    0.09
    éĹ´è·Ŀ
    0.08
     across
    0.08
     distance
    0.08
     distances
    0.08
    Activations Density 0.036%

    No Known Activations