© 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. 90826
    Prev
    Next
    INDEX
    Explanations

    EXBOX, vexforum, extrFocus

    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
    t
    -0.17
    e
    -0.15
    ty
    -0.13
    tl
    -0.13
    tc
    -0.12
    tre
    -0.12
    tv
    -0.12
    tle
    -0.12
    tu
    -0.12
    tin
    -0.12
    POSITIVE LOGITS
     Mahm
    0.09
    roud
    0.09
     garments
    0.09
    arin
    0.09
     Fut
    0.09
     infinit
    0.08
     accru
    0.08
     Barnett
    0.08
     perme
    0.08
     crane
    0.08
    Activations Density 0.006%

    No Known Activations