© 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. 37709
    Prev
    Next
    INDEX
    Explanations

    about, compared, illustrate, apply, access

    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
    aket
    -0.07
    olen
    -0.07
    Ñħодов
    -0.07
    ¦
    -0.07
    ariat
    -0.07
    çľĭåĪ°
    -0.06
    telen
    -0.06
    etzen
    -0.06
    ulares
    -0.06
    cules
    -0.06
    POSITIVE LOGITS
     farlo
    0.08
    plib
    0.08
    åħĪåľ¨
    0.07
    ipe
    0.07
    æľīçļĦåľ¨
    0.07
    è¿ĺæĺ¯åľ¨
    0.07
    è§ģäºİ
    0.07
    è®°èĢħåľ¨
    0.07
    åİĭåľ¨
    0.07
    icus
    0.07
    Activations Density 0.669%

    No Known Activations