© 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. 90972
    Prev
    Next
    INDEX
    Explanations

    as ... as or than comparisons

    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
     RI
    -0.11
    ota
    -0.09
    331
    -0.09
     excel
    -0.09
    REN
    -0.09
    ves
    -0.09
    -With
    -0.09
     threshold
    -0.09
    746
    -0.09
     ri
    -0.09
    POSITIVE LOGITS
     equivalent
    0.09
     Equivalent
    0.09
     Courtesy
    0.09
     worse
    0.09
    Equivalent
    0.09
     consistency
    0.08
     twice
    0.08
     subt
    0.08
    wor
    0.08
     Worse
    0.08
    Activations Density 0.092%

    No Known Activations