© 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. 43198
    Prev
    Next
    INDEX
    Explanations

    separating clauses or list items

    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
     appunto
    -0.08
     ÐĺÑĤак
    -0.07
    ↵↵
    -0.07
    æ¡¥éķĩ
    -0.07
    /apt
    -0.07
     коÑĤоÑĢÑĭÑħ
    -0.07
    ä¹ĥ
    -0.07
    嫦
    -0.06
    ä¸ĭ称
    -0.06
     Sebasti
    -0.06
    POSITIVE LOGITS
    ï¼Ľ
    0.07
    ;
    0.07
    èĻ½æĺ¯
    0.06
    èĻ½çĦ¶ä¸įæĺ¯
    0.06
    ä¸įçŁ¥éģĵçļĦ
    0.06
    %;
    0.06
    ulon
    0.06
    ;**
    0.06
    èĻ½çĦ¶æľī
    0.06
    大èĥĨçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations