© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56825
    Prev
    Next
    INDEX
    Explanations

    " Archive", " Archive", " Archive"

    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
    称
    -0.07
    åİŁ
    -0.06
    çĭ¬
    -0.06
    ³
    -0.06
    ibold
    -0.06
    强
    -0.06
    éĻ·
    -0.06
    ä¸įæŃ£å¸¸
    -0.06
    èį£
    -0.05
    éĤ£éĩĮ
    -0.05
    POSITIVE LOGITS
    ngine
    0.09
    ehme
    0.08
    è¯ĬæĸŃåıĬ
    0.08
    enha
    0.08
    zia
    0.08
    äh
    0.08
    enho
    0.08
    èĢħ们
    0.08
    åĬłç´¢
    0.07
    ndata
    0.07
    Activations Density 0.155%

    No Known Activations