© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57797
    Prev
    Next
    INDEX
    Explanations

    special characters followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    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
    aways
    -0.09
    udu
    -0.09
    /tab
    -0.08
    /is
    -0.08
     Territories
    -0.08
    tery
    -0.08
     Nobody
    -0.08
    hg
    -0.08
    iden
    -0.08
    thers
    -0.08
    POSITIVE LOGITS
    ï¸
    0.10
     elk
    0.09
    afe
    0.09
    ohan
    0.08
    ooo
    0.08
     boo
    0.08
    wig
    0.08
    FW
    0.08
     optionally
    0.08
     flock
    0.07
    Activations Density 0.015%

    No Known Activations