© 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. 55205
    Prev
    Next
    INDEX
    Explanations

    checking validity

    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
     embodiment
    -0.08
    apo
    -0.07
    éĻħ
    -0.07
    æĹº
    -0.07
    é©ħ
    -0.07
    hee
    -0.07
    inste
    -0.07
    Æ°ng
    -0.06
    umont
    -0.06
     exaggerated
    -0.06
    POSITIVE LOGITS
    ä¸įçĶ¨æĭħå¿ĥ
    0.09
    Ens
    0.08
    _BINARY
    0.08
    Ùħبر
    0.08
     ensuring
    0.08
    ä¿Ŀè¯ģ
    0.08
    ç¡®ä¿Ŀ
    0.08
     garant
    0.07
    lest
    0.07
     sufficient
    0.07
    Activations Density 0.002%

    No Known Activations