© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46686
    Prev
    Next
    INDEX
    Explanations

    software processes and washing

    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
    ilhar
    -0.08
    ihkan
    -0.07
     BHY
    -0.07
    bile
    -0.07
    aÅĤ
    -0.07
     bile
    -0.07
    éĢļçļĦ
    -0.07
    azor
    -0.07
    ãģĭãģı
    -0.06
    abeth
    -0.06
    POSITIVE LOGITS
    _specific
    0.08
    ver
    0.07
    áro
    0.07
     punc
    0.07
    å¾Īåı¯èĥ½
    0.07
    æīįè¡Į
    0.07
    åĬ¿åľ¨å¿ħ
    0.07
    æľªçŁ¥
    0.06
    éļıå¤Ħåı¯è§ģ
    0.06
    纨
    0.06
    Activations Density 0.010%

    No Known Activations