© 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. 41982
    Prev
    Next
    INDEX
    Explanations

    Selection of products

    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
    .").
    -0.08
    —which
    -0.08
     whichever
    -0.07
    æ¸ħæ´ģåį«çĶŁ
    -0.07
    ellent
    -0.07
     ê°ĢëĬ¥íķĺë©°
    -0.07
    æĤ£èĢħåľ¨
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.07
    èĥ½å¤ŁéĢļè¿ĩ
    -0.07
    arrer
    -0.07
    POSITIVE LOGITS
    ...**
    0.10
    âĢ¦**
    0.09
    æĢİä¹ĪåĬŀ
    0.08
     trotzdem
    0.07
    %**
    0.07
    ]**
    0.07
    åĽ½
    0.06
    éĹ²çĿĢ
    0.06
    kki
    0.06
    %</
    0.06
    Activations Density 0.182%

    No Known Activations