© 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. 5098
    Prev
    Next
    INDEX
    Explanations

    where to start or look

    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
     Alma
    -0.10
    feld
    -0.10
     democr
    -0.10
    moth
    -0.10
    fb
    -0.09
     Mell
    -0.09
     Neck
    -0.09
     abstract
    -0.09
    à¸ĵ
    -0.09
     Schwarz
    -0.09
    POSITIVE LOGITS
     nearest
    0.13
     else
    0.11
     nor
    0.09
     or
    0.09
    pu
    0.09
     advent
    0.09
    æĪĸ
    0.09
    ven
    0.09
     Cay
    0.08
    izu
    0.08
    Activations Density 0.010%

    No Known Activations