© 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. 43010
    Prev
    Next
    INDEX
    Explanations

    conditional code blocks

    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
    çł´å¤©
    -0.07
    ToUpdate
    -0.07
    ä¸įå°±æĺ¯
    -0.06
    anner
    -0.06
    åĶ
    -0.06
    apr
    -0.06
    é¡»ç»ı
    -0.06
     arra
    -0.06
    çŃĴ
    -0.06
    ä»İåīį
    -0.06
    POSITIVE LOGITS
    å¦Ĥæŀľ
    0.15
    èĭ¥æĺ¯
    0.14
    èĭ¥åľ¨
    0.14
     ë§Įìķ½
    0.14
    If
    0.14
    èĭ¥
    0.14
    å¦Ĥæŀľä¸Ģ个
    0.14
    å¦Ĥæŀľè¢«
    0.13
    —if
    0.13
    å¦Ĥæŀľåľ¨
    0.13
    Activations Density 0.078%

    No Known Activations