© 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. 13841
    Prev
    Next
    INDEX
    Explanations

    incorrectlydoubtedwrongflagged

    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
    çľ¼åīį
    -0.08
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    orni
    -0.07
    à¸Ńยูà¹Īà¹ģลà¹īว
    -0.07
    åī©ä¸ĭ
    -0.07
    ä¸įæķ£
    -0.07
    ntp
    -0.07
    åī©
    -0.07
    æĺĨ
    -0.07
    herits
    -0.07
    POSITIVE LOGITS
    åħ±ç®¡
    0.07
     Coastal
    0.07
    åıªåĽł
    0.07
     considers
    0.07
    çºłæŃ£
    0.07
     incorrect
    0.07
    ssa
    0.07
    elis
    0.07
     incorrectly
    0.07
    aab
    0.07
    Activations Density 0.016%

    No Known Activations