© 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. 89480
    Prev
    Next
    INDEX
    Explanations

    is known

    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
     Booth
    -0.09
    INTR
    -0.09
     Ger
    -0.09
    uma
    -0.09
    575
    -0.08
    ,âĢ¦
    -0.08
    595
    -0.08
     Hier
    -0.08
    oft
    -0.08
     pleased
    -0.08
    POSITIVE LOGITS
     ing
    0.09
     dec
    0.09
    icker
    0.09
    yy
    0.09
     granddaughter
    0.09
     sacks
    0.08
    itar
    0.08
     snapping
    0.08
     duplex
    0.08
     dew
    0.08
    Activations Density 1.517%

    No Known Activations