© 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. 9687
    Prev
    Next
    INDEX
    Explanations

    doi links and urls

    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
    渣
    -0.07
    å±±æĻ¯åĮº
    -0.07
    lude
    -0.07
    yli
    -0.07
    kow
    -0.07
    êu
    -0.07
    ạng
    -0.07
    iÅŁ
    -0.07
    åı¯ä»¥çĶ³è¯·
    -0.07
    رج
    -0.07
    POSITIVE LOGITS
    åįĹè¡Ĺ
    0.07
     rab
    0.06
    çģµ
    0.06
    claimed
    0.06
    åįĹé£İ
    0.06
    posti
    0.06
    onan
    0.06
    tori
    0.06
    éĿĪ
    0.06
    aven
    0.06
    Activations Density 0.007%

    No Known Activations