© 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. 62237
    Prev
    Next
    INDEX
    Explanations

    to and air

    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
    Ư
    -0.08
    esm
    -0.07
    .metro
    -0.07
    æīĢåĪĹ
    -0.07
    Ûķر
    -0.07
    ä¸įåħ¥
    -0.07
    importe
    -0.07
     parha
    -0.07
    achines
    -0.07
    å§ĭèĩ³
    -0.07
    POSITIVE LOGITS
    åı¯ä¾Ľ
    0.13
    åı¯ä»¥çĶ¨æĿ¥
    0.12
     Äijá»ĥ
    0.10
    çĶ¨æĿ¥
    0.10
     ÑĩÑĤобÑĭ
    0.09
    åı¯ä¾ĽéĢīæĭ©
    0.09
    çĶ¨ä»¥
    0.09
    åı¯çĶ¨äºİ
    0.09
    åı¯çĶ¨çļĦ
    0.08
    è¶³å¤ŁçļĦ
    0.08
    Activations Density 0.110%

    No Known Activations