© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 251
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¹¢
    -0.23
     CreateMap
    -0.22
     ×Ķ×ķ×ĵ
    -0.20
     ServiceException
    -0.20
     BusinessException
    -0.19
     Marketable
    -0.19
     gratuites
    -0.19
    amy
    -0.19
     timespec
    -0.19
    ç¤ħ
    -0.19
    POSITIVE LOGITS
     void
    0.40
     public
    0.37
     private
    0.34
    void
    0.30
    public
    0.30
     protected
    0.28
    private
    0.27
     def
    0.27
    .@
    0.26
     static
    0.24
    Activations Density 0.806%

    No Known Activations