© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30213
    Prev
    Next
    INDEX
    Explanations

    divided into sections or stages

    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
    िस
    -0.09
    bund
    -0.08
    anium
    -0.08
    leigh
    -0.08
    è¿«
    -0.08
    ếm
    -0.08
    colar
    -0.08
    代ãĤıãĤĬãģ«
    -0.08
    ottom
    -0.08
    legg
    -0.07
    POSITIVE LOGITS
    两éĥ¨åĪĨ
    0.10
    æŃ¥éª¤
    0.10
     steps
    0.10
    两个æĸ¹éĿ¢
    0.09
     step
    0.09
    ÑĩаÑģÑĤи
    0.08
     phases
    0.08
    ä¸īéĥ¨åĪĨ
    0.08
    æŃ¥é©Ł
    0.08
     stages
    0.07
    Activations Density 0.041%

    No Known Activations