© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11831
    Prev
    Next
    INDEX
    Explanations

    code structure or comments

    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
    ënt
    -0.08
    odont
    -0.08
    æ¸Ĭ
    -0.07
    esas
    -0.07
    osate
    -0.07
     latter
    -0.07
    ésil
    -0.07
    ÐłÐĿ
    -0.07
    esh
    -0.07
    kaar
    -0.07
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.08
    俱ä¹IJéĥ¨
    0.08
    ä¸Ģ个
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    身临åħ¶å¢ĥ
    0.08
    缸è¾ħ缸æĪIJ
    0.07
    it
    0.07
    ä¸Ģ个ç®ĢåįķçļĦ
    0.07
    èĢ³çĨŁèĥ½è¯¦
    0.07
    Activations Density 0.013%

    No Known Activations