© 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. 39983
    Prev
    Next
    INDEX
    Explanations

    indeed followed by comma

    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
    craft
    -0.08
    ä¸įåīį
    -0.08
    æĪijæĿ¥è¯´
    -0.08
     addirittura
    -0.08
    好èĩªå·±çļĦ
    -0.08
    аÑģÑĤ
    -0.08
    å°½æĥħ享åıĹ
    -0.08
    ιαί
    -0.08
    anoia
    -0.08
    <|box_end|>
    -0.07
    POSITIVE LOGITS
    ly
    0.11
    że
    0.08
     Äijặn
    0.07
     halnya
    0.07
    elijk
    0.07
     váºŃy
    0.07
    lichkeit
    0.07
    erness
    0.07
    heiten
    0.07
    MessageType
    0.07
    Activations Density 0.009%

    No Known Activations