© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7194
    Prev
    Next
    INDEX
    Explanations

    Copyright, dates, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    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
    usc
    -0.11
    amel
    -0.10
     Brandon
    -0.09
     ë¶Ģ
    -0.09
     Duch
    -0.09
    asel
    -0.09
     GEO
    -0.09
    _PB
    -0.09
     Dunk
    -0.09
    atten
    -0.09
    POSITIVE LOGITS
    allo
    0.08
    ï¸
    0.08
     hast
    0.08
    -bs
    0.08
     Ple
    0.08
     Og
    0.07
    eno
    0.07
     Intermediate
    0.07
    oga
    0.07
    <quote
    0.07
    Activations Density 0.070%

    No Known Activations