© 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. 19430
    Prev
    Next
    INDEX
    Explanations

    symmetric, shear, waves, IPS, antibiotic

    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
    è¿ĻäºĽåľ°æĸ¹
    -0.07
    stell
    -0.07
    å°ĶçļĦ
    -0.07
    /reset
    -0.07
    ekin
    -0.07
    è¿ĻäºĽäºº
    -0.06
     maf
    -0.06
    اعÙħ
    -0.06
    igers
    -0.06
     tempat
    -0.06
    POSITIVE LOGITS
    ushman
    0.08
    西æŀĹ
    0.08
    à¹Ģà¸ŀศ
    0.08
    ä¹Łç§°ä¸º
    0.07
    ottes
    0.07
    nikov
    0.07
    nen
    0.07
    pared
    0.07
    -dominated
    0.07
    çī¹æľīçļĦ
    0.07
    Activations Density 0.007%

    No Known Activations