© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21984
    Prev
    Next
    INDEX
    Explanations

    eternity and forever

    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
    sez
    -0.08
    æĺ¨å¤ľ
    -0.08
    å°Ķå¤ļ
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    çł´å¤©
    -0.08
    ered
    -0.08
     rÃł
    -0.08
    ioned
    -0.08
    plings
    -0.08
    -Encoding
    -0.08
    POSITIVE LOGITS
    ä¸įåıĺçļĦ
    0.11
    ä¸įçģŃ
    0.11
    ä¸įæľ½
    0.10
    ç¶ļãģı
    0.10
    lasting
    0.10
     forever
    0.10
    æ°¸æģĴçļĦ
    0.09
    åŁºä¸ļ
    0.09
     Forever
    0.09
    ä¸įåıĺ
    0.09
    Activations Density 0.032%

    No Known Activations