© 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. 89052
    Prev
    Next
    INDEX
    Explanations

    comes from

    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
     ostensibly
    -0.19
     glean
    -0.18
     invariably
    -0.18
     squarely
    -0.17
     purported
    -0.17
     requisite
    -0.15
     decidedly
    -0.14
     touted
    -0.14
     unwitting
    -0.14
     lament
    -0.14
    POSITIVE LOGITS
     hereby
    0.15
     preca
    0.13
     amongst
    0.11
     personals
    0.11
     Nowadays
    0.11
     nowadays
    0.10
     benefici
    0.10
     tho
    0.10
     independ
    0.10
     consequ
    0.10
    Activations Density 1.504%

    No Known Activations