© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    Carvalho, Chehab, Moumtzis

    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
    åŃĺåľ¨
    -0.07
    缮
    -0.07
    anna
    -0.07
    个åĽŀçŃĶ
    -0.07
    ãĢĮ
    -0.06
     cocks
    -0.06
    å¾ģ
    -0.06
    boo
    -0.06
    ç½®ä¹ĭ
    -0.06
     taps
    -0.06
    POSITIVE LOGITS
    issi
    0.09
    ynth
    0.08
    ä¸Ģæ°Ķ
    0.07
    ossi
    0.07
    ipel
    0.07
    社ä¼ļåĬĽéĩı
    0.07
    jord
    0.07
    asca
    0.07
    à¹Īาà¸Ļ
    0.07
    ä¸Ŀä¸Ŀ
    0.07
    Activations Density 0.005%

    No Known Activations