© 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. 38479
    Prev
    Next
    INDEX
    Explanations

    as far as I know

    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
    çŁ¥éģĵåIJĹ
    -0.10
    plusplus
    -0.08
    é¡»çŁ¥
    -0.08
     przecież
    -0.08
    çĽ¸ä¼ł
    -0.08
    çľĭçľĭåIJ§
    -0.07
    æĪijåIJĹ
    -0.07
    ódio
    -0.07
    utt
    -0.07
    hora
    -0.07
    POSITIVE LOGITS
    认为æĺ¯
    0.08
    æľªè§ģ
    0.08
    åĪĻ认为
    0.07
    æľī以ä¸ĭ
    0.07
    认为
    0.07
    ä»İ没
    0.07
    屯
    0.06
    elman
    0.06
     myself
    0.06
    æľª
    0.06
    Activations Density 0.983%

    No Known Activations