© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 644
    Prev
    Next
    INDEX
    Explanations

    appropriate, sufficient, enough

    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
    ucci
    -0.11
     Fortune
    -0.09
    isco
    -0.09
    fav
    -0.09
     fortune
    -0.09
    å½ķ
    -0.09
    asl
    -0.08
     duk
    -0.08
    izin
    -0.08
    ovi
    -0.08
    POSITIVE LOGITS
    /to
    0.14
    /app
    0.12
     amount
    0.12
     postage
    0.11
    /un
    0.11
     sized
    0.10
     proportions
    0.10
    /not
    0.10
     enough
    0.10
     ÑĩÑĤобÑĭ
    0.09
    Activations Density 1.165%

    No Known Activations