© 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. 348
    Prev
    Next
    INDEX
    Explanations

    Bassetti, Stoner, Mecel, Warren, JR

    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
     bust
    -0.07
    <|fim_suffix|>
    -0.07
    itzer
    -0.07
     ig
    -0.07
    izzard
    -0.06
     ((!
    -0.06
     capitals
    -0.06
    _iters
    -0.06
    bp
    -0.06
     Dud
    -0.06
    POSITIVE LOGITS
    ÑĤеÑĢ
    0.11
     Brut
    0.11
    pressions
    0.11
    gorm
    0.10
    aeda
    0.10
     Wend
    0.10
    toi
    0.10
    %E
    0.10
     Agr
    0.09
    latable
    0.09
    Activations Density 3.205%

    No Known Activations