© 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. 2049
    Prev
    Next
    INDEX
    Explanations

    thus/hence/therefore introducing results

    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
     обаÑĩе
    -0.09
     hingegen
    -0.08
    imenta
    -0.07
    ä»¿ä½Ľæĺ¯
    -0.07
    еÑģÑĤв
    -0.07
    ä¹ĭæīĢ以
    -0.07
     totiž
    -0.07
    however
    -0.07
    thora
    -0.07
    çīĩçļĦ
    -0.07
    POSITIVE LOGITS
    forth
    0.10
    å¾Ĺä¸Ĭ
    0.09
     its
    0.08
     [].
    0.08
    å¾ĹåIJį
    0.08
    ly
    0.08
    но
    0.07
    -called
    0.07
    /or
    0.07
    /OR
    0.07
    Activations Density 0.032%

    No Known Activations