© 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. 42634
    Prev
    Next
    INDEX
    Explanations

    isotope

    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
    æķĽ
    -0.06
    иÑģÑĮ
    -0.06
    man
    -0.06
    lify
    -0.06
    è¿ĩåİ»
    -0.06
    ines
    -0.06
    atch
    -0.06
    å±ħä½ıåľ°
    -0.06
    finity
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
    째
    0.09
    á»ħu
    0.08
    ήμε
    0.08
    gesamt
    0.08
    genden
    0.08
    ocab
    0.08
    æµģãĤĮ
    0.08
    à§įষ
    0.08
    onis
    0.07
    æĹ¥åIJİçļĦ
    0.07
    Activations Density 0.008%

    No Known Activations