© 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. 20751
    Prev
    Next
    INDEX
    Explanations

    laughter and suggestions

    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
     notoriously
    -0.09
    åį´å§ĭç»Ī
    -0.08
    æ°¸è¿ľ
    -0.07
    å§ĭç»Īæĺ¯
    -0.07
    å¸ĥ满
    -0.07
     relentlessly
    -0.07
     always
    -0.07
     invariably
    -0.07
     everywhere
    -0.07
     supposedly
    -0.07
    POSITIVE LOGITS
     possibly
    0.11
    åı¯èĥ½æĺ¯
    0.11
     probabilmente
    0.10
    æĪĸ许æľī
    0.10
    æľīåı¯èĥ½æĺ¯
    0.10
     likely
    0.10
    åı¯èĥ½éľĢè¦ģ
    0.10
     möglicherweise
    0.10
     perhaps
    0.10
     probably
    0.10
    Activations Density 0.004%

    No Known Activations