© 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. 6770
    Prev
    Next
    INDEX
    Explanations

    mutual, shared, common

    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
     together
    -0.11
     jointly
    -0.09
     accompanying
    -0.09
     collectively
    -0.09
     joint
    -0.09
    adoras
    -0.09
     prima
    -0.09
    inct
    -0.09
     swaps
    -0.09
    ill
    -0.08
    POSITIVE LOGITS
     interests
    0.10
    alfa
    0.10
     Jad
    0.10
     interest
    0.10
    ities
    0.10
     assignable
    0.09
    (delegate
    0.09
     VIA
    0.09
     acknow
    0.09
     desire
    0.09
    Activations Density 0.009%

    No Known Activations