© 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. 90230
    Prev
    Next
    INDEX
    Explanations

    response or reply

    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
    |max
    -0.11
    acs
    -0.10
    rott
    -0.10
     gag
    -0.10
    emax
    -0.10
    azon
    -0.09
     PROT
    -0.09
    821
    -0.09
    infer
    -0.09
    yne
    -0.09
    POSITIVE LOGITS
     crypt
    0.11
     that
    0.10
     with
    0.10
    crypt
    0.09
     via
    0.09
     unint
    0.09
     simply
    0.08
     entitled
    0.08
    erm
    0.08
    avec
    0.08
    Activations Density 0.011%

    No Known Activations