© 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. 32665
    Prev
    Next
    INDEX
    Explanations

    straight consecutive right through

    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
     Sloan
    -0.08
    :",↵
    -0.07
     Denied
    -0.07
     AAC
    -0.07
     écrit
    -0.07
    ии
    -0.07
     thrust
    -0.06
    :"↵
    -0.06
     tant
    -0.06
     Olive
    -0.06
    POSITIVE LOGITS
    lek
    0.12
    lify
    0.11
     suits
    0.11
     precisely
    0.11
     Elk
    0.11
    ILER
    0.10
     Hugo
    0.10
     beside
    0.10
     Dunk
    0.10
    ONA
    0.10
    Activations Density 0.001%

    No Known Activations