© 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. 48439
    Prev
    Next
    INDEX
    Explanations

    fast, time, minimal

    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
     непÑĢави
    -0.08
     mechanically
    -0.07
     unlimited
    -0.07
    oyo
    -0.07
    abase
    -0.07
    森
    -0.06
     unrestricted
    -0.06
    etter
    -0.06
     Unlimited
    -0.06
    è¿Ļæĺ¯å¯¹
    -0.06
    POSITIVE LOGITS
    éļIJèĶ½
    0.16
    -hidden
    0.16
    éļIJåĮ¿
    0.15
     invisible
    0.14
    éļIJèĹı
    0.14
    Hidden
    0.14
    invisible
    0.14
     hidden
    0.14
    hidden
    0.14
    éļIJèĹıåľ¨
    0.13
    Activations Density 0.272%

    No Known Activations