© 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. 58688
    Prev
    Next
    INDEX
    Explanations

    good and safe outcomes

    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
    åıįæŃ£
    -0.08
    åħ¨åĬĽåģļ好
    -0.08
    obel
    -0.07
    å¾Ĺ天çĭ¬
    -0.07
    åѤ
    -0.07
    æĶ¹åıĺçļĦ
    -0.07
     territoriale
    -0.07
     ditem
    -0.07
    .experimental
    -0.07
    aroo
    -0.07
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.13
     enough
    0.11
    ly
    0.10
    åĴĮæľī
    0.09
    åĴĮèī¯å¥½çļĦ
    0.08
    ness
    0.08
    -looking
    0.08
    nes
    0.08
    lier
    0.08
    Enough
    0.08
    Activations Density 0.184%

    No Known Activations