© 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. 38880
    Prev
    Next
    INDEX
    Explanations

    listing punctuation

    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
    éĩij森
    -0.09
    gang
    -0.08
    _RB
    -0.08
     Postar
    -0.08
    ä½Ĩåĩ¡
    -0.08
    åĩ¡æľ¬ç½ij注æĺİ
    -0.08
    å²Ľ
    -0.08
    ’B
    -0.08
    γÏĩ
    -0.08
    ãĤīãģĦ
    -0.08
    POSITIVE LOGITS
    åĪĿæŃ¥
    0.08
     preliminary
    0.07
    ash
    0.06
    ifer
    0.06
    final
    0.06
     Prel
    0.06
    以åıĬ对
    0.06
    acker
    0.06
    plus
    0.06
    ager
    0.06
    Activations Density 0.009%

    No Known Activations