© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    checking and assessment

    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
    æĥ³åĩº
    -0.07
    astia
    -0.07
    éĨį
    -0.07
    æĥ³çĶ¨
    -0.07
    antemente
    -0.06
    æĥ³èµ·
    -0.06
    -scalable
    -0.06
    reh
    -0.06
    ulong
    -0.06
    åĬŀ好
    -0.06
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.15
     ìŬë¶Ģ를
    0.14
     checks
    0.14
    Check
    0.13
     check
    0.13
     Check
    0.13
    æĿ¥åĪ¤æĸŃ
    0.13
     ìŬë¶Ģ
    0.13
    æ£ĢæŁ¥
    0.13
     checking
    0.13
    Activations Density 0.285%

    No Known Activations