© 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. 34611
    Prev
    Next
    INDEX
    Explanations

    what or unknown

    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
    çļĦåIJĹ
    -0.07
    åĹİ
    -0.07
    ickname
    -0.07
     (!((
    -0.07
    amus
    -0.07
    ilename
    -0.07
    åIJĹ
    -0.07
    lexible
    -0.07
    olina
    -0.07
    åħ¨å®¶
    -0.07
    POSITIVE LOGITS
    究竣æĺ¯
    0.12
    æĺ¯åIJ¦ä¸º
    0.11
    ä½Ĩèĩ³å°ij
    0.11
     exact
    0.11
    Exact
    0.10
     exactly
    0.10
     exactamente
    0.10
     apakah
    0.10
    æĺ¯åIJ¦ä¼ļ
    0.10
     whether
    0.09
    Activations Density 0.565%

    No Known Activations