© 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. 19966
    Prev
    Next
    INDEX
    Explanations

    names starting with Bern

    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
    å·´æİĮ
    -0.07
    ç»İ
    -0.07
     Berger
    -0.06
     ÑģоÑĢ
    -0.06
    å®¶åľ¨
    -0.06
    éĢĨæµģ
    -0.06
    è°į
    -0.06
    å°±åı«
    -0.06
    acht
    -0.06
    èij£
    -0.06
    POSITIVE LOGITS
    illot
    0.08
    pins
    0.08
    gnore
    0.08
    velt
    0.07
    Negative
    0.07
    çĴIJ
    0.07
    .googlecode
    0.07
    à¸Ľà¸²à¸ĩ
    0.07
    rone
    0.07
    rosso
    0.07
    Activations Density 0.001%

    No Known Activations