© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114161
    Prev
    Next
    INDEX
    Explanations

    software license

    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
     incl
    -0.09
    icha
    -0.09
     Handy
    -0.09
     blackmail
    -0.09
    aket
    -0.08
     sniff
    -0.08
     ($.
    -0.08
    umbo
    -0.08
    erti
    -0.08
     cuff
    -0.08
    POSITIVE LOGITS
    pwd
    0.10
    Cri
    0.09
    iec
    0.09
     Treasure
    0.09
     Bryant
    0.09
    PCI
    0.09
     Scandin
    0.09
    aked
    0.09
     somew
    0.09
    shint
    0.09
    Activations Density 0.001%

    No Known Activations