© 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. 62916
    Prev
    Next
    INDEX
    Explanations

    .java file paths

    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
    ç»Ħç»ĩæŀ¶æŀĦ
    -0.08
     sök
    -0.08
    agrid
    -0.08
    FromClass
    -0.08
    å¢ĥçļĦ
    -0.07
    é«ĺå¯Ĩ
    -0.07
    常è§ģçĹħ
    -0.07
    说ä»Ģä¹Ī
    -0.07
    åĽ¢ç»ĵä¸Ģèĩ´
    -0.07
    ossip
    -0.07
    POSITIVE LOGITS
    achable
    0.07
    йо
    0.06
    rin
    0.06
    DN
    0.06
    滨河
    0.06
     gry
    0.06
    _tD
    0.06
    ä¸įæĢķ
    0.06
    ify
    0.06
    2
    0.06
    Activations Density 0.045%

    No Known Activations