© 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. 28931
    Prev
    Next
    INDEX
    Explanations

    Liberty Science, Stadium, Police, Mutual, Counsel

    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
    akin
    -0.10
    lein
    -0.09
     reb
    -0.08
    .nlm
    -0.08
    unk
    -0.08
    ivet
    -0.08
    apon
    -0.08
    sgiving
    -0.07
    lass
    -0.07
    Modifier
    -0.07
    POSITIVE LOGITS
    ally
    0.13
    .awtextra
    0.12
    RARY
    0.12
    aries
    0.12
    irie
    0.12
    arians
    0.12
    rarian
    0.11
    chten
    0.11
    raries
    0.11
    oux
    0.11
    Activations Density 0.070%

    No Known Activations