© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    compiler errors and warnings

    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
     impost
    -0.09
    orns
    -0.09
    ija
    -0.09
    umbs
    -0.09
    pher
    -0.09
    quier
    -0.09
    agus
    -0.09
    cus
    -0.08
     shl
    -0.08
     Ner
    -0.08
    POSITIVE LOGITS
     Relevant
    0.10
    fight
    0.09
     Wells
    0.08
     equ
    0.08
    ind
    0.08
    (or
    0.08
    789
    0.08
     loin
    0.08
     trick
    0.08
    ’,
    0.07
    Activations Density 0.001%

    No Known Activations