© 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. 31179
    Prev
    Next
    INDEX
    Explanations

    #include

    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
    buquerque
    -0.09
    -bel
    -0.09
    ç«Ļç«Ļ
    -0.08
     Allem
    -0.08
    _MAT
    -0.08
    ajak
    -0.08
    мбÑĥ
    -0.08
    ç´IJ
    -0.07
     Smarty
    -0.07
    ashi
    -0.07
    POSITIVE LOGITS
    æľĪèĢĥ
    0.06
    rm
    0.06
    rash
    0.06
    saf
    0.06
    inë
    0.06
     Flach
    0.06
     ØŃÙĬ
    0.05
     Cust
    0.05
    çĶ¨äºİ
    0.05
    in
    0.05
    Activations Density 0.034%

    No Known Activations