© 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. 30502
    Prev
    Next
    INDEX
    Explanations

    signed agreements and licenses

    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
     tolerance
    -0.11
     tolerated
    -0.10
     пÑĢод
    -0.08
     ?>↵↵↵
    -0.08
    /bar
    -0.08
     toler
    -0.08
     Nelson
    -0.08
     Pruitt
    -0.08
    ullet
    -0.08
     Bal
    -0.08
    POSITIVE LOGITS
     signed
    0.43
     signing
    0.42
     Signing
    0.38
     Signed
    0.35
     paperwork
    0.35
    -signed
    0.34
    Signing
    0.31
     contracts
    0.30
    Signed
    0.30
     signatures
    0.29
    Activations Density 0.249%

    No Known Activations