© 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. 1949
    Prev
    Next
    INDEX
    Explanations

    and

    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
    åħ¶ä»ĸ
    -0.27
    elts
    -0.26
     ?><?
    -0.26
    ereotype
    -0.25
    olicited
    -0.24
     pageNo
    -0.23
    使çĶ¨èĢħæĪĸ
    -0.23
    tá
    -0.22
    abyrin
    -0.22
    å¹³æ°ij
    -0.22
    POSITIVE LOGITS
    /or
    0.78
     thus
    0.45
     hence
    0.40
    rogen
    0.38
     therefore
    0.38
     then
    0.38
    /OR
    0.38
    åĽłæѤ
    0.36
     vice
    0.35
    rog
    0.34
    Activations Density 2.664%

    No Known Activations