© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39693
    Prev
    Next
    INDEX
    Explanations

    sharp tools and blades

    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
     blobs
    -0.10
    æijĩ
    -0.08
     Blob
    -0.08
     blob
    -0.08
     cola
    -0.07
    пл
    -0.07
    ç³Ĭ
    -0.07
    adre
    -0.07
    çļ®çIJĥ
    -0.07
     ballo
    -0.07
    POSITIVE LOGITS
    éĶĭåĪ©
    0.18
    éĶĭåĪ©çļĦ
    0.15
    éĶĭ
    0.14
    åĪĥ
    0.13
    éĶĭèĬĴ
    0.13
     sharpen
    0.13
    åĪĢåĪĥ
    0.13
    éĭĴ
    0.12
    åĪĢåħ·
    0.12
     sharp
    0.12
    Activations Density 0.127%

    No Known Activations