© 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. 55821
    Prev
    Next
    INDEX
    Explanations

    specific attributes

    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
    åĢ¼çļĦ
    -0.09
    çļĦè¿IJçĶ¨
    -0.08
    使çĶ¨æĿĥ
    -0.08
    ç»ĵæŀľæĺ¯
    -0.08
    çļĦ使çĶ¨æĸ¹æ³ķ
    -0.08
    çļĦåĬĽåº¦
    -0.07
    å°½æĺ¯
    -0.07
    ä¸Ģçݯ
    -0.07
    çļĦåIJİæŀľ
    -0.07
    ahoo
    -0.07
    POSITIVE LOGITS
    åŁºæľ¬ä¿¡æģ¯
    0.12
    æľ¬èº«çļĦ
    0.11
    -specific
    0.11
     specifics
    0.09
     parameters
    0.09
    -related
    0.09
     attributes
    0.09
    åŁºæľ¬æĥħåĨµ
    0.09
     characteristics
    0.09
    çļĦä¸ĢäºĽ
    0.09
    Activations Density 0.067%

    No Known Activations