© 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. 57404
    Prev
    Next
    INDEX
    Explanations

    except for

    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
    rather
    -0.08
    没åķ¥
    -0.08
    èĢĮéĿŀ
    -0.07
    åģļä¸ĢäºĽ
    -0.07
    è¿ĺæľīä¸ĢäºĽ
    -0.07
    å¾Īå¤ļéĹ®é¢ĺ
    -0.07
     allerlei
    -0.07
    å¾Īå¤ļä¸ľè¥¿
    -0.07
    ä¸įèĥ½åĨį
    -0.07
    ä¹Łæľīä¸ĢäºĽ
    -0.07
    POSITIVE LOGITS
     except
    0.18
    Except
    0.16
    except
    0.16
     Except
    0.15
     kecuali
    0.15
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.14
    羣æŃ£
    0.13
     sauf
    0.13
     ever
    0.13
     EVER
    0.12
    Activations Density 0.288%

    No Known Activations