© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    REQUEST_METHOD

    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
    ŃĶ
    -0.06
    åĻ
    -0.06
    ä¸ĢæĬĬ
    -0.05
    ìłĪ
    -0.05
    åIJ«ç¬ij
    -0.05
    _literals
    -0.05
    é¦Ļæ²¹
    -0.05
    alach
    -0.05
    gar
    -0.05
     perk
    -0.05
    POSITIVE LOGITS
    uet
    0.08
    æĹłåĩł
    0.08
    åħ±åIJĮåĬªåĬĽä¸ĭ
    0.08
    ihn
    0.08
    rib
    0.08
    Ỽn
    0.08
    æ»ĭäºĭ
    0.08
    édi
    0.08
    uve
    0.07
    stoff
    0.07
    Activations Density 0.064%

    No Known Activations