© 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. 37548
    Prev
    Next
    INDEX
    Explanations

    ideal, unlimited, or ideal cases

    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
    -anchor
    -0.08
    ä½İè°ĥ
    -0.07
    _checks
    -0.07
    çĽ¸å¯¹ç¨³å®ļ
    -0.07
    éľĢè¦ģåIJĮ
    -0.07
    对人类
    -0.07
    _ALIGNMENT
    -0.07
     zar
    -0.07
    æļ®
    -0.07
     fragment
    -0.07
    POSITIVE LOGITS
     infinite
    0.08
     unlimited
    0.08
     unrealistic
    0.08
    æĹłçĹķ
    0.07
     limitless
    0.07
    оÑĤе
    0.07
     incapable
    0.07
    æĹł
    0.07
     Unlimited
    0.07
    елÑı
    0.07
    Activations Density 0.007%

    No Known Activations