© 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. 7533
    Prev
    Next
    INDEX
    Explanations

    convex polygon

    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
     bare
    -0.08
     Bare
    -0.07
    å¼
    -0.07
     kopi
    -0.07
    èĢĥ
    -0.07
    rin
    -0.07
    ç²¾åĩĨ
    -0.06
    annon
    -0.06
    èĢĥè¯ģ
    -0.06
     dén
    -0.06
    POSITIVE LOGITS
    åĩ¸
    0.09
     convex
    0.09
    kis
    0.08
    otos
    0.08
    ierz
    0.08
     enclosing
    0.08
    utt
    0.08
    imli
    0.08
    _conv
    0.07
    çĶ»æ³ķ
    0.07
    Activations Density 0.001%

    No Known Activations