© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    other

    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
     Seger
    -0.08
    rine
    -0.07
    asca
    -0.07
    jän
    -0.07
    Ã¤ÃŁig
    -0.07
    chetti
    -0.07
     Pager
    -0.07
     kro
    -0.06
     conveniently
    -0.06
    emy
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.10
    åħ¶å®ĥ
    0.10
     exceptions
    0.10
    åħ¶å®ĥçļĦ
    0.10
     other
    0.09
    åħ¶ä»ĸæĸ¹å¼ı
    0.09
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.09
    çļĦåħ¶ä»ĸ
    0.09
    ä¾ĭå¤ĸ
    0.09
    åı¦ç±»
    0.09
    Activations Density 0.480%

    No Known Activations