© 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. 20754
    Prev
    Next
    INDEX
    Explanations

    paid, one, the

    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
     anyway
    -0.08
    esame
    -0.07
    ืà¸Ńà¸Ļ
    -0.07
     sonst
    -0.07
    ened
    -0.06
    è¿ĺæľīå°±æĺ¯
    -0.06
    çļĦåIJĮæŶ
    -0.06
    âĨĵâĨĵ
    -0.06
    åĨį说äºĨ
    -0.06
     ÙħعÙĩÙħ
    -0.06
    POSITIVE LOGITS
    èĻ½çĦ¶ä¸įæĺ¯
    0.10
    ).-
    0.09
    èĻ½çĦ¶
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    å¦Ĥåħ¶
    0.08
    缸æ¯Ķäºİ
    0.08
    缸è¾ĥäºİ
    0.08
    éī´äºİ
    0.08
    èĻ½çĦ¶æ²¡æľī
    0.07
    itera
    0.07
    Activations Density 0.010%

    No Known Activations