© 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. 17201
    Prev
    Next
    INDEX
    Explanations

    reach the end or finish

    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
    为äºĨæĽ´å¥½åľ°
    -0.09
    à¹Īาย
    -0.08
    çĥŃçĥĪ欢è¿İ
    -0.07
    ears
    -0.07
    hetto
    -0.07
    μÏİν
    -0.07
    åħįè´¹åĴ¨è¯¢
    -0.07
    mom
    -0.07
     Svil
    -0.07
    åĩłç§ĴéĴŁ
    -0.07
    POSITIVE LOGITS
    ä»ĺæ¸ħ
    0.07
    äºĭåĬ¡æīĢ
    0.07
    _outline
    0.07
     prescrit
    0.07
    è®
    0.07
    æľĢå¿«çļĦ
    0.07
    åħ¨éĥ¨è¯Ħ论
    0.07
    éĿ¢åīįçļĦ
    0.07
    à¹ĥหà¹īà¹Ħà¸Ķà¹ī
    0.07
    尽快
    0.06
    Activations Density 0.047%

    No Known Activations