© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    edith, big, how, shocked, config, console

    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
     Bands
    -0.09
     thumbs
    -0.09
    (and
    -0.09
    ysi
    -0.09
     tro
    -0.09
    pis
    -0.08
    ibs
    -0.08
     bah
    -0.08
    eva
    -0.08
    oms
    -0.08
    POSITIVE LOGITS
    DN
    0.10
    rac
    0.09
    dn
    0.09
     Voy
    0.09
     Owen
    0.09
     Kod
    0.09
    ?!
    0.09
    915
    0.09
     nap
    0.09
     tract
    0.08
    Activations Density 0.199%

    No Known Activations