© 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. 24131
    Prev
    Next
    INDEX
    Explanations

    surnames followed by initials or suffixes

    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
     Tutt
    -0.08
     Purt
    -0.07
    gau
    -0.07
     startX
    -0.07
    kent
    -0.07
     cuckold
    -0.07
     Hubb
    -0.07
    schild
    -0.07
    ä¸Ģ空
    -0.07
     runApp
    -0.07
    POSITIVE LOGITS
     eds
    0.11
     colleagues
    0.08
    ãģ¨ãĤĤãģ«
    0.08
     others
    0.07
     editors
    0.07
     ê·¸ë¦¬ê³ł
    0.07
     associates
    0.06
    others
    0.06
     dal
    0.06
    æľīåħ³è¦ģæ±Ĥ
    0.06
    Activations Density 0.106%

    No Known Activations