© 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. 15002
    Prev
    Next
    INDEX
    Explanations

    some are

    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
     mostly
    -0.11
     one
    -0.09
    boro
    -0.09
     Mostly
    -0.08
    ä¸Ģ个
    -0.08
     chiefly
    -0.08
    æľĢ
    -0.08
     mainly
    -0.08
     fastest
    -0.08
     another
    -0.08
    POSITIVE LOGITS
     hybrids
    0.16
     downright
    0.14
     scams
    0.14
     standalone
    0.13
     collaborations
    0.13
     repeats
    0.12
     actually
    0.12
    nt
    0.12
    /w
    0.11
     reminiscent
    0.11
    Activations Density 0.152%

    No Known Activations