© 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. 17045
    Prev
    Next
    INDEX
    Explanations

    picking probability

    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
    iphers
    -0.08
    ç¯ĩäºĮ
    -0.08
    tings
    -0.08
    ÐĹÐŀ
    -0.08
    nern
    -0.08
     retribu
    -0.08
    aszt
    -0.07
     pathname
    -0.07
    viders
    -0.07
     favicon
    -0.07
    POSITIVE LOGITS
     **
    0.08
    ↵
    0.07
    BAT
    0.07
    姥
    0.07
     ne
    0.06
    æł¸å¿ĥ
    0.06
    åħ³éŨ
    0.06
     *
    0.06
    aden
    0.06
    æ´ŀ
    0.06
    Activations Density 0.002%

    No Known Activations