© 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. 33506
    Prev
    Next
    INDEX
    Explanations

    space between them

    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
    ä¹ĭ称çļĦ
    -0.08
    onda
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    ä¹ĭ乡
    -0.08
    arily
    -0.08
    nya
    -0.08
    åħ¶ä¸Ńä¸Ģ个
    -0.08
    lina
    -0.08
    onton
    -0.08
    缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.07
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.12
     lévÅij
    0.08
    åľ°å¤´
    0.08
    Ø©
    0.08
    éļĻ
    0.07
    åŃĺåľ¨çĿĢ
    0.07
    çļĦäºĭåĬ¡
    0.07
    гоÑĢ
    0.07
    以åıĬä¸İ
    0.07
    -sama
    0.07
    Activations Density 0.007%

    No Known Activations