© 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. 61311
    Prev
    Next
    INDEX
    Explanations

    punctuation and phrases starting with periods

    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
    ç¾İ人
    -0.07
    lund
    -0.07
    inken
    -0.07
    _hide
    -0.07
    ç§ĭæľĪ
    -0.07
    yson
    -0.07
    é«ĺ人
    -0.07
    è¿Ļä¸ĢçĤ¹
    -0.07
    åľ°è¢«
    -0.06
    åİĨéĻ©
    -0.06
    POSITIVE LOGITS
    æł¹æį®æĿĥåĪ©è¦ģæ±Ĥ
    0.07
    rail
    0.07
     assorted
    0.07
    äºĪåijĬ
    0.07
    mass
    0.07
    èĽ®
    0.07
    orz
    0.07
     masses
    0.06
    对éĤ£äºĽ
    0.06
    urtle
    0.06
    Activations Density 0.018%

    No Known Activations