© 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. 88878
    Prev
    Next
    INDEX
    Explanations

    consisting of

    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
    aler
    -0.10
     Spicer
    -0.10
     gob
    -0.09
     leftovers
    -0.09
    (after
    -0.09
    annes
    -0.09
     nip
    -0.09
     nett
    -0.09
     Incre
    -0.08
     eg
    -0.08
    POSITIVE LOGITS
     consisting
    0.22
     composed
    0.17
    —which
    0.16
    composed
    0.16
    —a
    0.15
     which
    0.15
     comprised
    0.15
    which
    0.13
     consisted
    0.13
    —an
    0.13
    Activations Density 0.334%

    No Known Activations