© 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. 32924
    Prev
    Next
    INDEX
    Explanations

    buy, pay, sing, verify

    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
     Craig
    -0.11
     using
    -0.08
     Lamb
    -0.08
     based
    -0.08
    oba
    -0.08
    based
    -0.08
    iri
    -0.08
    ena
    -0.07
     Terry
    -0.07
    atel
    -0.07
    POSITIVE LOGITS
     purposes
    0.15
    instead
    0.14
     instead
    0.14
    udge
    0.14
     indirectly
    0.13
    ificate
    0.11
    jah
    0.11
    undry
    0.11
    Instead
    0.11
    allen
    0.11
    Activations Density 0.616%

    No Known Activations