© 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. 28497
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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
     Tune
    -0.09
    ossa
    -0.09
    idon
    -0.08
    onis
    -0.08
     Legendary
    -0.08
     Berger
    -0.08
     Patt
    -0.08
    oldt
    -0.08
    yx
    -0.08
     Fal
    -0.07
    POSITIVE LOGITS
    adow
    0.11
     PMC
    0.09
     neger
    0.09
    arching
    0.09
     interpre
    0.09
    ambi
    0.09
    ings
    0.09
     round
    0.09
     entire
    0.09
     iface
    0.08
    Activations Density 0.021%

    No Known Activations