© 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. 22224
    Prev
    Next
    INDEX
    Explanations

    disappear, eliminated

    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
    两ä¸į误
    -0.07
    ä¸īéĿ¢
    -0.07
    OU
    -0.07
     wid
    -0.06
    leman
    -0.06
    ä»ĸæīį
    -0.06
    åħ¬ç§ģ
    -0.06
     pali
    -0.06
    åıĪä¸į失
    -0.06
    ç§ijåѦåѦéĻ¢
    -0.06
    POSITIVE LOGITS
    æ¶Ī失
    0.17
    æ¶Ī失äºĨ
    0.16
    åıĸæ¶Ī
    0.16
     disappears
    0.15
    ä¸įåĨį
    0.15
     disappear
    0.15
    没æľīäºĨ
    0.14
     иÑģÑĩез
    0.14
     eliminated
    0.14
    åıĸæ¶ĪäºĨ
    0.14
    Activations Density 0.488%

    No Known Activations