© 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. 4916
    Prev
    Next
    INDEX
    Explanations

    Puerto Ricans, Vienna, SunRail, Allied Waste, Palm Beach, lesbian, wax vaporizers

    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
    _crypto
    -0.07
    .ssl
    -0.06
    thora
    -0.06
    åģ¥åº·å®īåħ¨
    -0.06
    ivs
    -0.06
    TextChanged
    -0.06
    ell
    -0.06
    entro
    -0.06
     rem
    -0.06
    åij¨å²ģ以ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    immel
    0.08
    सर
    0.08
    _imm
    0.07
    ediat
    0.07
    个æ¡Ī
    0.07
     mj
    0.07
     ÑħодÑĥ
    0.07
    轩è¾ķ
    0.07
    ç´«
    0.06
    arat
    0.06
    Activations Density 0.557%

    No Known Activations