© 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. 29205
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    illos
    -0.10
    fare
    -0.08
     Hond
    -0.08
     kost
    -0.08
     resc
    -0.08
    IJ
    -0.08
     wedge
    -0.08
     deadlock
    -0.07
    ypy
    -0.07
     fare
    -0.07
    POSITIVE LOGITS
     ordin
    0.10
     Ou
    0.10
     overweight
    0.09
     Afterwards
    0.09
     seins
    0.09
     exemplary
    0.09
    BI
    0.09
     unl
    0.09
     Quentin
    0.09
     genitals
    0.09
    Activations Density 0.001%

    No Known Activations