© 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. 115369
    Prev
    Next
    INDEX
    Explanations

    ev + following word

    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
    ellig
    -0.10
     bord
    -0.10
    inant
    -0.10
    eworthy
    -0.10
     roughly
    -0.09
    erate
    -0.09
    bate
    -0.09
    enheim
    -0.09
     Kerry
    -0.09
    ered
    -0.09
    POSITIVE LOGITS
     ev
    0.15
     Ev
    0.15
     Evil
    0.12
     EV
    0.12
    ansion
    0.12
    Ev
    0.11
     Anth
    0.11
     Eva
    0.11
    .respond
    0.10
    aporation
    0.10
    Activations Density 0.020%

    No Known Activations