© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27506
    Prev
    Next
    INDEX
    Explanations

    response to prompts

    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
    omid
    -0.10
    çĽ
    -0.09
    odom
    -0.08
     succeed
    -0.08
    oba
    -0.08
     surrogate
    -0.07
     compreh
    -0.07
    clus
    -0.07
     lav
    -0.07
     compr
    -0.07
    POSITIVE LOGITS
     thereof
    0.12
    arsed
    0.11
    ARSE
    0.11
     sÃŃ
    0.10
    avar
    0.10
     doch
    0.10
     appraisal
    0.10
     overhead
    0.10
     appropriations
    0.10
     rot
    0.10
    Activations Density 0.151%

    No Known Activations