© 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. 46871
    Prev
    Next
    INDEX
    Explanations

    help but

    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
    dzi
    -0.09
     hook
    -0.09
    aler
    -0.09
     uncompressed
    -0.09
     Instit
    -0.09
     bf
    -0.09
     hell
    -0.09
     legitimately
    -0.08
    gf
    -0.08
     hend
    -0.08
    POSITIVE LOGITS
     being
    0.18
     overhe
    0.13
     noticing
    0.13
     thinking
    0.13
    being
    0.13
     wondering
    0.12
    lessly
    0.12
     believing
    0.11
     feeling
    0.11
     Notices
    0.11
    Activations Density 0.008%

    No Known Activations