© 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. 24029
    Prev
    Next
    INDEX
    Explanations

    directed for

    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
    åĩºçİ°åľ¨
    -0.07
    è¿ĻæŶåĢĻ
    -0.07
     dabei
    -0.07
    è¿Ļ个æŶåĢĻ
    -0.06
    åľ¨è¿Ļ个æŶåĢĻ
    -0.06
    èĹıåľ¨
    -0.06
    åĩºçı¾åľ¨
    -0.06
    åľ¨è¿Ļ
    -0.06
    è¿Ļç§įæĸ¹å¼ı
    -0.06
    éĩĮéĿ¢æľī
    -0.06
    POSITIVE LOGITS
    afort
    0.10
    mma
    0.08
    upon
    0.08
    ëŀĺ
    0.08
    (er
    0.08
    ools
    0.08
    uÅĤ
    0.08
    ulah
    0.08
    åı¯è¨Ģ
    0.08
    çĦī
    0.08
    Activations Density 0.149%

    No Known Activations