© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 649
    Prev
    Next
    INDEX
    Explanations

    citations

    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
    ().'/
    -0.33
    hipster
    -0.28
    ngth
    -0.28
    .omg
    -0.26
    sexy
    -0.25
    éĩĩçŁ¿çŃī
    -0.24
    åħ¶å®ĥéĹ®é¢ĺ
    -0.24
    libft
    -0.23
    esteem
    -0.23
    :".$
    -0.23
    POSITIVE LOGITS
    .
    0.24
     MouseButton
    0.21
    ):?>↵
    0.21
    å¨ĵ
    0.20
    ä¸Ģæĺ¯
    0.19
    see
    0.18
    .↵
    0.18
     Wroc
    0.18
    arn
    0.18
    忺
    0.18
    Activations Density 0.545%

    No Known Activations