© 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. 91615
    Prev
    Next
    INDEX
    Explanations

    writing and feedback

    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
     cl
    -0.09
     pole
    -0.09
     bif
    -0.09
     stubborn
    -0.08
     stub
    -0.08
     capit
    -0.08
    locks
    -0.08
     Paras
    -0.08
     Dew
    -0.08
     Pole
    -0.08
    POSITIVE LOGITS
    .echo
    0.10
     OTHERWISE
    0.10
     Membership
    0.10
     membership
    0.10
     Graz
    0.09
    urat
    0.09
     extinct
    0.09
     Scarlett
    0.09
     posto
    0.09
     scar
    0.09
    Activations Density 0.003%

    No Known Activations