© 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. 46095
    Prev
    Next
    INDEX
    Explanations

    last number of versions

    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
    pcm
    -0.07
    orne
    -0.06
    mö
    -0.06
    ÄĻg
    -0.06
    owns
    -0.06
     exotic
    -0.06
    ä¸įæĺİçļĦ
    -0.06
    æŶ令
    -0.06
    说å¾Ĺ
    -0.06
    ãģ¡ãģª
    -0.06
    POSITIVE LOGITS
     clones
    0.08
     clone
    0.08
    nak
    0.08
    ä¼ĺ缺çĤ¹
    0.08
     rewritten
    0.08
    åıĸéķ¿è¡¥çŁŃ
    0.08
    ç½²åIJį
    0.07
     submitted
    0.07
    ä¸į足ä¹ĭå¤Ħ
    0.07
    éĥ½ä¸įéĶĻ
    0.07
    Activations Density 0.004%

    No Known Activations