© 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. 89146
    Prev
    Next
    INDEX
    Explanations

    explaining meaning or consequence

    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
    vsp
    -0.12
    entes
    -0.12
    /db
    -0.11
    ,strong
    -0.11
     PRI
    -0.11
     Winn
    -0.11
     ourselves
    -0.11
    zw
    -0.11
    UMB
    -0.11
    Inline
    -0.11
    POSITIVE LOGITS
     that
    0.12
     something
    0.11
     nothing
    0.11
     either
    0.10
     they
    0.10
     exactly
    0.10
     he
    0.09
     trouble
    0.09
     there
    0.08
     somebody
    0.08
    Activations Density 0.037%

    No Known Activations