© 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. 33907
    Prev
    Next
    INDEX
    Explanations

    json/code structures with keywords like success, error, field, passed

    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
    áh
    -0.07
    æľīåIJį
    -0.06
    s
    -0.06
    ignon
    -0.06
    itre
    -0.06
    ("").
    -0.06
    ä¸īäºĶ
    -0.06
    äºļ
    -0.06
    å¯ĩ
    -0.06
    oron
    -0.06
    POSITIVE LOGITS
    azón
    0.08
    æī§è¡Į人
    0.08
    ç»ĵäºĨ
    0.07
    enggar
    0.07
    âĸĪ
    0.07
    _heap
    0.07
     szen
    0.07
    -env
    0.07
    åħ¥åº§
    0.07
    aned
    0.07
    Activations Density 0.014%

    No Known Activations