© 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. 24739
    Prev
    Next
    INDEX
    Explanations

    anodization

    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
    åĢ¼å¾ĹæľŁå¾ħ
    -0.09
    argout
    -0.08
    /goto
    -0.08
    æľªå®Įå¾ħç»Ń
    -0.08
    çŃīéĩį大
    -0.08
    /epl
    -0.08
    åĩ¤åĩ°ç½ij
    -0.08
     à¸Ńà¹Īาà¸Ļà¸ķà¹Īà¸Ń
    -0.08
    биÑĤÑĮÑģÑı
    -0.08
     Ultimately
    -0.08
    POSITIVE LOGITS
    ãģ§ä½ľ
    0.06
    <strong
    0.06
    æĺ¯ä¸Ģ家以
    0.05
     ì¶ľìĭł
    0.05
    0.05
    Unnamed
    0.05
    (Source
    0.05
    åĪ°åºĹ
    0.04
    æĺ¯åħ³éĶ®
    0.04
    åĪĽå»ºäºİ
    0.04
    Activations Density 18.268%

    No Known Activations