© 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. 50595
    Prev
    Next
    INDEX
    Explanations

    verbs followed by infinitive 'to'"

    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
    heen
    -0.08
    juh
    -0.07
    embre
    -0.07
    brica
    -0.07
    èįĴèĬľ
    -0.07
    eldom
    -0.07
    å¾·æĸ¯
    -0.06
    åŁºå°¼
    -0.06
    并åħ·æľī
    -0.06
    ä¼ļåıĺå¾Ĺ
    -0.06
    POSITIVE LOGITS
    ä¸įæĸĻ
    0.09
    å°±åľ¨è¿ĻæŶ
    0.09
    æīĵç®Ĺ
    0.09
    以为
    0.09
    没æĥ³åĪ°
    0.08
    éļıåı£
    0.08
    è°ģçŁ¥
    0.08
     обаÑĩе
    0.08
    ukk
    0.08
    åį´è¢«
    0.08
    Activations Density 0.294%

    No Known Activations