© 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. 43806
    Prev
    Next
    INDEX
    Explanations

    journal mentions

    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
     pizz
    -0.07
    åħ¨éĥ¨è¯Ħ论
    -0.07
    ä¸įæĶ¾
    -0.07
    лай
    -0.07
    UserRole
    -0.06
    ardy
    -0.06
    ÑĢекÑĤоÑĢ
    -0.06
    esco
    -0.06
    INY
    -0.06
    _EXTERN
    -0.06
    POSITIVE LOGITS
    SEE
    0.07
     Symposium
    0.07
    补缺
    0.07
    okal
    0.07
    ä¸Ģå¤ķ
    0.07
    ÙĪاط
    0.07
     chÃŃ
    0.07
    AA
    0.07
    see
    0.06
    æĪijåIJĹ
    0.06
    Activations Density 0.023%

    No Known Activations