© 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. 26503
    Prev
    Next
    INDEX
    Explanations

    no such

    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
     respectfully
    -0.10
    arna
    -0.10
    sic
    -0.09
     Mellon
    -0.09
     {?}
    -0.09
    åĨĨ
    -0.09
    rift
    -0.09
    mek
    -0.09
    eken
    -0.09
     UNU
    -0.09
    POSITIVE LOGITS
    pe
    0.28
     dice
    0.18
     cigar
    0.15
    PE
    0.15
     sir
    0.15
    isy
    0.12
     chance
    0.12
     matter
    0.12
     Dice
    0.11
    oooo
    0.11
    Activations Density 0.030%

    No Known Activations