© 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. 57277
    Prev
    Next
    INDEX
    Explanations

    names

    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°Ĩè¾¾
    -0.06
    æ¸IJ
    -0.06
    éľĢè¦ģåħ·å¤ĩ
    -0.06
    å±Ĭ
    -0.06
    计ç®Ĺåħ¬å¼ı
    -0.06
    çĶ»ä¸Ĭ
    -0.06
    nhem
    -0.06
     magazines
    -0.06
    åħ·
    -0.06
    åľ¨çĻ½
    -0.06
    POSITIVE LOGITS
    實é«Ķ
    0.07
    ĥ½
    0.07
    igor
    0.07
    czyn
    0.07
    @d
    0.07
    asilan
    0.07
    áĥĶáĥłáĥĺ
    0.07
    ilter
    0.07
    åıĪæĿ¥äºĨ
    0.07
    rolley
    0.07
    Activations Density 0.150%

    No Known Activations