© 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. 17581
    Prev
    Next
    INDEX
    Explanations

    adverbial modifiers of action

    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
     formally
    -0.07
    æĦŁè§īå¾Ī
    -0.07
     briefly
    -0.07
    è¦ģä¿ĿæĮģ
    -0.06
     explicitly
    -0.06
    端æŃ£
    -0.06
    åĨĻå¾Ĺ
    -0.06
    åĬªåĬĽ
    -0.06
    å¯ĨåĪĩåħ³æ³¨
    -0.06
    ç¡®å®ļ为
    -0.06
    POSITIVE LOGITS
     dÃłng
    0.11
     léo
    0.10
    /false
    0.09
    ly
    0.09
     enough
    0.08
    ably
    0.08
    æŀģäºĨ
    0.08
    è¿ĩ渡
    0.08
    issime
    0.08
    (er
    0.08
    Activations Density 0.125%

    No Known Activations