© 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. 34465
    Prev
    Next
    INDEX
    Explanations

    destabilized, posting, lost, drained, created, display, drawn

    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
    #/
    -0.08
    è¿ĻäºĽæķ°æį®
    -0.07
    æ·³
    -0.07
    andi
    -0.07
    åľ°ç¨İ
    -0.07
    ropa
    -0.07
    itel
    -0.07
    è¿ĻäºĽéĥ½
    -0.07
    æľ¬åŃIJ
    -0.07
    æĺ¯äººä½ĵ
    -0.07
    POSITIVE LOGITS
    çĶļèĩ³
    0.08
    ustum
    0.08
    便
    0.07
    çĶļèĩ³åı¯ä»¥
    0.07
    çĶļèĩ³åľ¨
    0.07
     even
    0.07
    åŃ
    0.06
    çĶļèĩ³æĺ¯
    0.06
    ep
    0.06
    eyed
    0.06
    Activations Density 0.737%

    No Known Activations