© 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. 48502
    Prev
    Next
    INDEX
    Explanations

    Ron followed by a name

    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
    yte
    -0.10
    oppel
    -0.09
     outcome
    -0.08
    ocene
    -0.08
    zych
    -0.08
    ivism
    -0.08
     flush
    -0.08
    iddy
    -0.07
     fr
    -0.07
    ethe
    -0.07
    POSITIVE LOGITS
    ald
    0.17
    deaux
    0.12
    ny
    0.12
    nock
    0.11
    nak
    0.11
     Reagan
    0.11
    rone
    0.10
    nie
    0.10
     standby
    0.10
     Jeremy
    0.10
    Activations Density 0.017%

    No Known Activations