© 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. 27384
    Prev
    Next
    INDEX
    Explanations

    ellipsis followed by various phrases

    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
    ,...↵
    -0.10
     âĢº
    -0.10
    ,...
    -0.09
     alike
    -0.09
     pul
    -0.09
     ..."↵
    -0.09
     nid
    -0.09
     Gan
    -0.09
     gall
    -0.09
    ãĢĤãĢĤ
    -0.09
    POSITIVE LOGITS
    ike
    0.12
    orca
    0.10
    icc
    0.10
     Salvador
    0.10
    hei
    0.10
    awe
    0.09
     Nicola
    0.09
     ("<
    0.09
    hone
    0.09
     monstr
    0.09
    Activations Density 0.051%

    No Known Activations