© 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. 8499
    Prev
    Next
    INDEX
    Explanations

    different words

    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
    æĩIJ
    -0.07
    _PRINTF
    -0.07
    èĥľä»»
    -0.07
    رش
    -0.07
    edir
    -0.07
    æĺ¯å¤©
    -0.06
    itel
    -0.06
    cert
    -0.06
    ['_
    -0.06
    çļĦä¸Ģ个éĩįè¦ģ
    -0.06
    POSITIVE LOGITS
    æĮī
    0.08
     insgesamt
    0.08
    æķ´ä½ĵ
    0.07
    åIJĮæł·
    0.07
    è§Ħå¾ĭ
    0.07
    åĪĨéħį
    0.07
    åıĮéĩį
    0.07
    说æĺİ
    0.07
    uya
    0.07
    æĪijä¸Ģ个人
    0.07
    Activations Density 0.085%

    No Known Activations