© 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. 89430
    Prev
    Next
    INDEX
    Explanations

    going back or reversed

    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
    uman
    -0.08
     uni
    -0.08
     congress
    -0.08
     Gibraltar
    -0.08
    erot
    -0.08
    -elect
    -0.08
     strapped
    -0.08
    ongo
    -0.08
    imest
    -0.08
    onga
    -0.08
    POSITIVE LOGITS
     Lac
    0.11
    rell
    0.10
    anes
    0.10
    mpr
    0.10
     feas
    0.10
     sanity
    0.09
     practicing
    0.09
    lac
    0.09
     relationship
    0.09
     Sanity
    0.09
    Activations Density 0.001%

    No Known Activations