© 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. 34830
    Prev
    Next
    INDEX
    Explanations

    SQL join statements

    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
    ä¿Ĭ
    -0.06
    åĢ
    -0.06
    è¶Ł
    -0.06
    åĨ²
    -0.05
     einmal
    -0.05
    inj
    -0.05
    ç±
    -0.05
    åĶĩè§Ĵ
    -0.05
    imit
    -0.05
    ä¿Ŀ
    -0.05
    POSITIVE LOGITS
    "./
    0.08
    bucks
    0.08
    "."
    0.08
    onne
    0.08
     WHERE
    0.08
    ozilla
    0.08
     رÙĥ
    0.07
    ãģ¬
    0.07
    LOCKS
    0.07
    å¾Ĺåħ¶
    0.07
    Activations Density 0.130%

    No Known Activations