© 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. 89554
    Prev
    Next
    INDEX
    Explanations

    important to us

    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
     apl
    -0.13
    tes
    -0.11
     mini
    -0.11
    ec
    -0.10
    vim
    -0.09
    rost
    -0.09
    arie
    -0.09
     blended
    -0.09
     Mini
    -0.09
     ADM
    -0.09
    POSITIVE LOGITS
    VERY
    0.12
    very
    0.12
     VERY
    0.12
     very
    0.11
     indeed
    0.11
    çķĮ
    0.10
    inde
    0.09
     Kash
    0.09
     Manit
    0.09
     Corinth
    0.09
    Activations Density 0.756%

    No Known Activations