© 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. 26086
    Prev
    Next
    INDEX
    Explanations

    variety of kinds

    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
    azi
    -0.09
     Hispan
    -0.08
     hor
    -0.08
     loud
    -0.08
    -ra
    -0.08
    bish
    -0.08
     hem
    -0.07
     bubble
    -0.07
     sup
    -0.07
     voc
    -0.07
    POSITIVE LOGITS
    #ac
    0.10
     appealed
    0.10
     Sle
    0.09
    cad
    0.09
     indefinitely
    0.09
    umi
    0.09
    ục
    0.09
    emplace
    0.09
     Swan
    0.09
    usa
    0.09
    Activations Density 0.024%

    No Known Activations