© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    debt and creditors

    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
    itano
    -0.08
    iative
    -0.08
    åIJĦåľ°çļĦ
    -0.07
    utnik
    -0.07
    ialized
    -0.07
     vla
    -0.07
    <|box_end|>
    -0.07
    tação
    -0.07
    urnished
    -0.07
     chans
    -0.07
    POSITIVE LOGITS
    ottage
    0.08
    åĢºæĿĥ
    0.08
    æ¸ħåģ¿
    0.07
    å¾ĢæĿ¥
    0.07
    oppel
    0.07
    callable
    0.07
     Rond
    0.07
    ÑģÑĭпаÑĤÑĮ
    0.07
    å·²åħ¨éĥ¨
    0.07
    oppers
    0.06
    Activations Density 0.010%

    No Known Activations