© 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. 8633
    Prev
    Next
    INDEX
    Explanations

    academic paper authors

    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
    thumb
    -0.08
    exus
    -0.08
    åī¯ç»Ħéķ¿
    -0.08
     izle
    -0.08
    akwa
    -0.08
    èįŀ
    -0.08
    _RET
    -0.07
    xious
    -0.07
    quete
    -0.07
    |int
    -0.07
    POSITIVE LOGITS
    cev
    0.08
     physicists
    0.08
     algebra
    0.07
     unpublished
    0.07
     conject
    0.07
     applications
    0.07
     forthcoming
    0.07
     Algebra
    0.07
    æĸĩ稿
    0.06
     geometr
    0.06
    Activations Density 0.172%

    No Known Activations