© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7241
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    ÛĮÙĦÛĮ
    -0.09
    ij¸
    -0.09
    :?
    -0.08
    ãĤĤãģ®ãģ§ãģ¯
    -0.08
    åıĤåĬłåŁ¹è®Ń
    -0.08
    usra
    -0.08
     Phục
    -0.08
    Õ®
    -0.08
     neger
    -0.08
    mios
    -0.08
    POSITIVE LOGITS
    为æѤ
    0.09
    æīįè¡Į
    0.08
    è¿Ļå°±è¦ģæ±Ĥ
    0.07
    ä¹Łå°±æĺ¯
    0.07
    æĺ¾çĦ¶
    0.06
    è¿Ļå°±éľĢè¦ģ
    0.06
    æľĢç®Ģåįķ
    0.06
    è¿ĻéľĢè¦ģ
    0.06
    çľĭä¸Ĭ
    0.06
     v
    0.06
    Activations Density 0.022%

    No Known Activations