© 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. 16375
    Prev
    Next
    INDEX
    Explanations

    Junior or Jr. appended to names

    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
    esen
    -0.13
    onal
    -0.12
    lessly
    -0.11
    ench
    -0.11
    abled
    -0.10
     Round
    -0.10
    stone
    -0.10
     <=>
    -0.10
     rounding
    -0.09
    osoph
    -0.09
    POSITIVE LOGITS
    -most
    0.11
    orsch
    0.11
    .parseInt
    0.10
    -aged
    0.10
    -level
    0.10
    aturas
    0.09
    -vars
    0.09
    -league
    0.09
    Them
    0.08
    atur
    0.08
    Activations Density 0.033%

    No Known Activations