© 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. 26776
    Prev
    Next
    INDEX
    Explanations

    selecting specific items

    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
    pired
    -0.10
    oop
    -0.10
    anst
    -0.10
    ived
    -0.10
     profess
    -0.10
     drew
    -0.10
     rejecting
    -0.09
    -uppercase
    -0.09
     Took
    -0.09
    aded
    -0.09
    POSITIVE LOGITS
     removed
    0.17
     done
    0.15
     intact
    0.14
     replaced
    0.14
     taken
    0.14
     thrown
    0.14
     added
    0.14
     gone
    0.14
     included
    0.14
     preserved
    0.14
    Activations Density 0.165%

    No Known Activations