© 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. 50432
    Prev
    Next
    INDEX
    Explanations

    explanations for why

    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
    sten
    -0.12
    lez
    -0.11
     mint
    -0.11
     Mint
    -0.11
    yr
    -0.11
    ary
    -0.10
    ivan
    -0.10
    uffers
    -0.10
    ives
    -0.09
     MIT
    -0.09
    POSITIVE LOGITS
    /how
    0.29
    /if
    0.16
     bother
    0.16
     they
    0.15
    ever
    0.12
     we
    0.12
    te
    0.12
     she
    0.12
     else
    0.11
    soever
    0.11
    Activations Density 0.037%

    No Known Activations