© 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. 11264
    Prev
    Next
    INDEX
    Explanations

    words ending in 'lov' or 'olv'

    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
    ither
    -0.09
    æľ¬æ³ķ
    -0.08
    ä»ĸ们éľĢè¦ģ
    -0.08
    åij½
    -0.07
    Returned
    -0.07
    aldo
    -0.07
    -animate
    -0.07
    ÑĨи
    -0.07
     filib
    -0.07
    ä»Ļ女
    -0.07
    POSITIVE LOGITS
    _keyword
    0.07
    åľ¨éŁ©åĽ½
    0.07
    æ§ĺ
    0.07
    _suffix
    0.06
    lov
    0.06
    olv
    0.06
    ç»ıæµİ
    0.06
    боÑĢ
    0.06
     cer
    0.06
    åĻ©
    0.06
    Activations Density 0.183%

    No Known Activations