© 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. 47032
    Prev
    Next
    INDEX
    Explanations

    finding the right words

    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
    ajang
    -0.09
    æĺ¾èĢĮæĺĵ
    -0.08
    ASSES
    -0.08
    ToLocal
    -0.08
    nown
    -0.08
    shaw
    -0.07
    listed
    -0.07
    antos
    -0.07
    WithName
    -0.07
    ócr
    -0.07
    POSITIVE LOGITS
     wording
    0.14
     phrases
    0.12
     phrase
    0.11
    表述
    0.11
    æݪ
    0.11
     words
    0.11
     language
    0.10
    phrase
    0.09
    è¯Ńè¨Ģ
    0.09
    çŁŃè¯Ń
    0.09
    Activations Density 0.051%

    No Known Activations