© 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. 27395
    Prev
    Next
    INDEX
    Explanations

    phantom behavior

    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
    æĽ²æĬĺ
    -0.07
    ä¸ī段
    -0.06
    èµ°å®Į
    -0.06
    ä¸ĩ次
    -0.06
    æŬ
    -0.06
     mòn
    -0.06
     steps
    -0.06
     Verl
    -0.06
    缩çŁŃ
    -0.06
    æ¦Ľ
    -0.06
    POSITIVE LOGITS
     коÑģмо
    0.09
    æľ¬æĬ¥è®¯
    0.09
     inflation
    0.08
    æ¯Ĥ
    0.08
    á»ĩt
    0.08
     slashed
    0.08
    ç§ijæĬĢéĥ¨
    0.08
    schild
    0.08
     Pue
    0.08
    idr
    0.08
    Activations Density 0.002%

    No Known Activations