© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16708
    Prev
    Next
    INDEX
    Explanations

    ended with or up

    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
    /pm
    -0.10
    imest
    -0.10
    OA
    -0.10
    yers
    -0.10
    rique
    -0.10
    ANTE
    -0.09
     topped
    -0.09
    onso
    -0.09
    bote
    -0.09
    heimer
    -0.09
    POSITIVE LOGITS
     with
    0.14
     differently
    0.12
     badly
    0.10
     predict
    0.10
     BAD
    0.10
     trag
    0.10
     in
    0.10
     Nack
    0.09
     happily
    0.09
    angers
    0.09
    Activations Density 0.030%

    No Known Activations