© 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. 23082
    Prev
    Next
    INDEX
    Explanations

    within those

    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
    agh
    -0.07
    ieten
    -0.07
     ì±Ħ
    -0.07
    éģ¿
    -0.07
    çĻ
    -0.07
    è§Ħ
    -0.07
    端åĪ°
    -0.07
    æ´»
    -0.07
    ä¼į
    -0.07
    eos
    -0.06
    POSITIVE LOGITS
    ored
    0.08
    åħ³æ³¨æĪij
    0.07
     locator
    0.07
    ÙĦÙĬØ©
    0.07
     ÑĢаÑģположениÑı
    0.07
    ιÏĥη
    0.07
     gege
    0.07
     worth
    0.06
    aat
    0.06
    ORTE
    0.06
    Activations Density 0.001%

    No Known Activations