© 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. 65186
    Prev
    Next
    INDEX
    Explanations

    time to

    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
    å¸Ĥæĸ°
    -0.08
    ihan
    -0.08
    ught
    -0.08
    å¿»
    -0.08
    å§Ĩæĸ¯
    -0.07
    uhl
    -0.07
    /welcome
    -0.07
    erset
    -0.07
    ctors
    -0.07
    ĥ
    -0.07
    POSITIVE LOGITS
    ä¸įä½ıäºĨ
    0.07
    å¿«çĤ¹
    0.07
    éĹ®é¢ĺæĿ¥äºĨ
    0.07
    fila
    0.07
    ä¹Łä¸įå°ij
    0.06
    注æĦıçļĦæĺ¯
    0.06
    aku
    0.06
    !),
    0.06
    æĢİä¹ĪåĬŀ
    0.06
     encer
    0.06
    Activations Density 0.007%

    No Known Activations