© 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. 13590
    Prev
    Next
    INDEX
    Explanations

    technological or procedural descriptors

    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
    ĥĿ
    -0.07
    <|box_end|>
    -0.07
    çļĦæīĢæľīä½ľåĵģ
    -0.07
    /or
    -0.06
    å·¡è§Ĩåijĺ
    -0.06
    èĥ½è§ģ度
    -0.06
    ãĤ¿ãĥªãĤ¢
    -0.06
    çĮľçĮľ
    -0.06
    .Disclaimer
    -0.06
    (?:
    -0.06
    POSITIVE LOGITS
    oplay
    0.08
    elen
    0.08
    acket
    0.07
    anche
    0.07
    å§Ĩ
    0.07
    ént
    0.07
    åĦ¿çļĦ
    0.06
    ewise
    0.06
    åĦ¿
    0.06
    åĪĨ许
    0.06
    Activations Density 3.194%

    No Known Activations