© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87797
    Prev
    Next
    INDEX
    Explanations

    sameness or interchangeability

    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
    Negative Logits
    ITH
    -0.10
    ium
    -0.09
    /document
    -0.09
     Contrast
    -0.09
     unlike
    -0.08
    ippers
    -0.08
     contrasting
    -0.08
     Rey
    -0.08
     contrast
    -0.08
    inch
    -0.08
    POSITIVE LOGITS
     Same
    0.28
    Same
    0.27
    same
    0.27
     same
    0.26
     essentially
    0.24
     SAME
    0.23
    _same
    0.23
     semantics
    0.23
    åIJĮ
    0.22
     accompl
    0.22
    Activations Density 0.292%

    No Known Activations