© 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. 49971
    Prev
    Next
    INDEX
    Explanations

    studies and findings

    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
     reportedly
    -0.14
    ahi
    -0.12
     IMO
    -0.11
    kur
    -0.11
     rumored
    -0.10
     according
    -0.10
    ÂŃt
    -0.10
    atab
    -0.10
    according
    -0.10
     Cres
    -0.10
    POSITIVE LOGITS
     indeed
    0.15
     conclus
    0.13
     surprisingly
    0.13
     statistically
    0.13
     concluding
    0.13
     overwhelmingly
    0.12
     consistently
    0.12
     meas
    0.11
     concluded
    0.11
     atleast
    0.10
    Activations Density 1.436%

    No Known Activations