© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    frequency difference

    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
    åıĸå¾ĹçļĦæĪIJ绩
    -0.08
    çĤ
    -0.07
    Indented
    -0.07
    aths
    -0.07
    æ¯ıå¹³æĸ¹ç±³
    -0.06
    amai
    -0.06
    å±±åİ¿
    -0.06
    polis
    -0.06
    èķ¾
    -0.06
    çĶĺéľ²
    -0.06
    POSITIVE LOGITS
    uku
    0.09
    arget
    0.08
    åĮ¹éħį
    0.08
    _matching
    0.08
    phon
    0.08
    éŨæĪ·
    0.07
    requencies
    0.07
    ingo
    0.07
    enu
    0.07
     momentum
    0.07
    Activations Density 0.003%

    No Known Activations