© 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. 111710
    Prev
    Next
    INDEX
    Explanations

    once again

    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
    oin
    -0.10
     Weiter
    -0.09
    erez
    -0.09
    alin
    -0.09
    alia
    -0.09
    .hxx
    -0.09
    enti
    -0.09
    ancia
    -0.09
     sometimes
    -0.09
    ä¹Ī
    -0.09
    POSITIVE LOGITS
     proving
    0.11
     Wag
    0.09
     proves
    0.09
    onders
    0.08
    emy
    0.08
    iving
    0.08
    keh
    0.08
     demonstrating
    0.08
    sav
    0.08
     dealing
    0.08
    Activations Density 0.008%

    No Known Activations