© 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. 24904
    Prev
    Next
    INDEX
    Explanations

    variants

    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
    rowable
    -0.08
    rece
    -0.07
    oplevel
    -0.07
    ãĥĥãĤŃ
    -0.07
    cio
    -0.07
    obble
    -0.07
    æľºåŀĭ
    -0.07
     Grove
    -0.07
    ulence
    -0.06
    scoped
    -0.06
    POSITIVE LOGITS
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    0.12
    Depending
    0.11
    ä¸įä¸Ģå®ļ
    0.11
     Depending
    0.11
    æľªå¿ħ
    0.11
    å¾Īåı¯èĥ½
    0.09
     depending
    0.09
     often
    0.09
    å¾Ģå¾Ģ
    0.09
    ä¸įä¸Ģå®ļæĺ¯
    0.09
    Activations Density 0.265%

    No Known Activations