© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44453
    Prev
    Next
    INDEX
    Explanations

    compound random, complete monotonicity, quasi one-dimensional, repeater, immortal neuronal, ANA nucleoside, Cayley trees

    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
    Negative Logits
    usercontent
    -0.09
    ruzzo
    -0.09
    aeper
    -0.08
    aturen
    -0.08
    ä¸įåı¯æĢķ
    -0.08
    issance
    -0.08
    à¥įलà¥Ģ
    -0.08
    aranto
    -0.08
    aturas
    -0.08
    ejah
    -0.08
    POSITIVE LOGITS
    (?)
    0.07
    为åħ¶
    0.06
     (
    0.06
     (?)
    0.06
     kì
    0.06
    ä¸Ĭéĥ½
    0.06
    XB
    0.06
    RP
    0.06
     (=
    0.06
    åIJijåħ¶
    0.05
    Activations Density 0.458%

    No Known Activations