© 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. 60174
    Prev
    Next
    INDEX
    Explanations

    checking argument count

    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
    碰
    -0.09
    夫æĸ¯åŁº
    -0.08
    onas
    -0.08
    idora
    -0.08
    itamente
    -0.08
     prostytut
    -0.08
    éĴ»çłĶ
    -0.08
    èĥ§
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    ellino
    -0.07
    POSITIVE LOGITS
    å»ĸ
    0.06
    ä¸Ģèĩ³
    0.06
     paris
    0.06
    Ñħоз
    0.06
    é£İåIJ¹è¿ĩ
    0.06
    θοÏĤ
    0.06
     legion
    0.06
    å°Ĩä¸Ģ个
    0.06
    yn
    0.06
    ne
    0.06
    Activations Density 0.028%

    No Known Activations