© 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. 15544
    Prev
    Next
    INDEX
    Explanations

    proportional to

    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
    /or
    -0.09
    以å¤ĸçļĦ
    -0.07
    家家
    -0.07
    ewa
    -0.07
    çļĦé«ĺæĸ°æĬĢæľ¯
    -0.07
    riot
    -0.07
    ================
    -0.07
    两åİħ
    -0.07
    رج
    -0.07
    деле
    -0.07
    POSITIVE LOGITS
    ï¸İ
    0.10
    ä¹İåħ¶
    0.09
    /=
    0.08
    äºİä¸Ģ
    0.08
    pto
    0.08
    äºİæĺ¯
    0.08
    æĢ§åľ°
    0.08
    äºİå¿ĥ
    0.07
    ä¹İ
    0.07
    ï¸ı
    0.07
    Activations Density 0.002%

    No Known Activations