© 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. 4271
    Prev
    Next
    INDEX
    Explanations

    alternative STATE experimental else

    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
    åĨħæł¸
    -0.08
    lia
    -0.08
    oker
    -0.08
    ette
    -0.07
    æģªå®Ī
    -0.07
    isk
    -0.07
    ije
    -0.06
    ysin
    -0.06
    åħį
    -0.06
    稳å®ļ
    -0.06
    POSITIVE LOGITS
    æĺ¯ä¸ĢæĶ¯
    0.07
    -ready
    0.07
    Driven
    0.07
     tipi
    0.07
    alz
    0.07
    訴
    0.07
    èĥ¤
    0.07
     puj
    0.07
    æĶ¾åѦåIJİ
    0.07
    æĸ¹åIJij
    0.07
    Activations Density 0.001%

    No Known Activations