© 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. 91387
    Prev
    Next
    INDEX
    Explanations

    comparing with other things

    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
     wink
    -0.11
     shepherd
    -0.10
     disappe
    -0.10
    582
    -0.10
     realizing
    -0.09
     Winner
    -0.09
    omb
    -0.09
    Ñİ
    -0.09
    mdb
    -0.09
     precis
    -0.09
    POSITIVE LOGITS
     compared
    0.56
     compare
    0.47
     compares
    0.47
     comparison
    0.44
     Compared
    0.43
     comparative
    0.41
     Compare
    0.40
     comparisons
    0.40
     comparing
    0.37
     compar
    0.36
    Activations Density 0.644%

    No Known Activations