© 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. 40546
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

    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
    åħ¶ä¸º
    -0.08
    ree
    -0.07
    çļĦåIJĹ
    -0.06
    erged
    -0.06
    èĬĤæ°Ķ
    -0.06
    ç§ij
    -0.06
    sic
    -0.06
    å©Ģ
    -0.06
    icker
    -0.06
    éĶ¢
    -0.06
    POSITIVE LOGITS
    oces
    0.08
    abad
    0.07
    åĩºäºº
    0.07
    ×Ĵ×¢
    0.07
    è®¤çľŁè´Łè´£
    0.07
    rosse
    0.07
    ç»´äºļ
    0.07
    ubre
    0.07
    ócr
    0.07
    unders
    0.07
    Activations Density 0.005%

    No Known Activations