© 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. 42859
    Prev
    Next
    INDEX
    Explanations

    want to avoid

    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
    rog
    -0.09
    toff
    -0.08
     patern
    -0.07
    oko
    -0.07
    intree
    -0.07
    æĹłéĿŀ
    -0.07
    ystery
    -0.07
    orest
    -0.07
    -resources
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
    POSITIVE LOGITS
     implicitly
    0.09
     omission
    0.09
    解åĨ³åĬŀæ³ķ
    0.08
    解åĨ³è¿Ļ个éĹ®é¢ĺ
    0.08
    éģ¿åħįåĽł
    0.08
     technically
    0.08
    è§Ħéģ¿
    0.07
     automatically
    0.07
    éĺ²èĮĥæݪæĸ½
    0.07
     tac
    0.07
    Activations Density 0.019%

    No Known Activations