© 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. 29632
    Prev
    Next
    INDEX
    Explanations

    programming language list

    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
    spy
    -0.08
    ucci
    -0.07
    vus
    -0.07
    åĬłè½½æĽ´å¤ļ
    -0.07
    оÑĤоÑĢ
    -0.07
    uccio
    -0.07
    .getBytes
    -0.06
    å¹´å§ĭ
    -0.06
     Atta
    -0.06
    ç½¹
    -0.06
    POSITIVE LOGITS
    [++
    0.07
    .Adam
    0.07
    æĶ¾åľ¨ç¬¬ä¸Ģä½į
    0.07
    æĺ¯åħ¶
    0.07
    rief
    0.07
    -Jul
    0.06
    ISING
    0.06
    keen
    0.06
    çĹħæĥħåĪĨæŀIJ
    0.06
    äºĶ人
    0.06
    Activations Density 0.039%

    No Known Activations