© 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. 50914
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
     unavoid
    -0.08
    请ä¸ĭè½½
    -0.08
    ecker
    -0.08
    èĩ£
    -0.08
     Snowden
    -0.07
    åĽłèĢĮ
    -0.07
    æį®äºĨ解
    -0.07
     Starr
    -0.07
    ä¼ijåħ»
    -0.07
    åĽ¾ä¸ŃäºĮç»´çłģ
    -0.07
    POSITIVE LOGITS
    以ä¸ĭæŃ¥éª¤
    0.09
    ...\
    0.08
    æľī以ä¸ĭ
    0.07
    æ¢ĵ
    0.07
    çĨł
    0.07
    å®Ŀ
    0.07
    åħ·æľī以ä¸ĭ
    0.06
    gba
    0.06
    éĹĩ
    0.06
    loc
    0.06
    Activations Density 0.006%

    No Known Activations