© 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. 32395
    Prev
    Next
    INDEX
    Explanations

    groups followed by '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
    好ä¸į
    -0.07
    èµĦæĸĻæĺ¾ç¤º
    -0.06
    对åĨħ
    -0.06
    导èĩ´
    -0.06
    人被
    -0.06
    çĤ¹å¯¹
    -0.06
    人ä¸Ģ
    -0.06
    人们对äºİ
    -0.06
    å°»
    -0.06
     dime
    -0.06
    POSITIVE LOGITS
    ämään
    0.11
    —which
    0.09
     ׾×Ķ×Ļ×ķת
    0.09
     ׾×Ķת
    0.08
     να
    0.08
     ÑĩÑĤобÑĭ
    0.08
    åĩ«
    0.08
     to
    0.08
    —who
    0.08
    è¯ĿæĿ¥
    0.08
    Activations Density 0.368%

    No Known Activations