© 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. 33565
    Prev
    Next
    INDEX
    Explanations

    $\mathrm{km}\,s^{-1}$

    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
    reta
    -0.07
    éĤ£ä¸ªæŶåĢĻ
    -0.06
    Äĥr
    -0.06
    reti
    -0.06
    inat
    -0.06
    otr
    -0.06
    rtl
    -0.06
    åĢį
    -0.06
    åıijå±ķ模å¼ı
    -0.06
    à¹Ģà¸Ĺียม
    -0.06
    POSITIVE LOGITS
    Convertible
    0.09
    eté
    0.08
    almaz
    0.08
    ä½łè¿Ļæĺ¯
    0.08
    edly
    0.07
    uah
    0.07
    åĬłåħ¥æĶ¶èĹı
    0.07
    ifice
    0.07
    örd
    0.07
    fillable
    0.07
    Activations Density 0.001%

    No Known Activations