© 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. 57959
    Prev
    Next
    INDEX
    Explanations

    species names (e.g., "dea uliginosalis")

    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
    ’
    -0.09
    ‘
    -0.07
    âĢij
    -0.07
    âĢ
    -0.07
     (“
    -0.06
    “
    -0.06
     ‘
    -0.06
    å¦Ĥ
    -0.06
     atop
    -0.06
     “
    -0.06
    POSITIVE LOGITS
    opan
    0.09
    çµ
    0.09
    erja
    0.09
    aab
    0.08
    kaar
    0.08
    lable
    0.08
    forcer
    0.08
    olg
    0.08
    æłijä¸Ģ
    0.08
    æľīäºĽåľ°æĸ¹
    0.08
    Activations Density 0.002%

    No Known Activations