© 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. 60657
    Prev
    Next
    INDEX
    Explanations

    conversational connectors

    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
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.07
    女éĥİ
    -0.07
    uras
    -0.07
    æĮº
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    èĩªåªĴä½ĵå¹³åı°
    -0.07
    ...',
    -0.07
    ando
    -0.07
    å±ķå¼Ģåħ¨æĸĩ
    -0.07
    reeze
    -0.07
    POSITIVE LOGITS
     otherwise
    0.07
    иÑģÑĮ
    0.07
    åĵī
    0.07
    #__
    0.07
    áģĭ
    0.07
    Úº
    0.06
    .
    0.06
    eni
    0.06
    ighted
    0.06
    [dir
    0.06
    Activations Density 0.021%

    No Known Activations