© 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. 90126
    Prev
    Next
    INDEX
    Explanations

    true enough

    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
     stere
    -0.12
     stereotype
    -0.11
    .$.
    -0.10
     embell
    -0.10
     riv
    -0.10
     due
    -0.10
     elo
    -0.09
    iol
    -0.09
    moth
    -0.09
     saturated
    -0.09
    POSITIVE LOGITS
     notwithstanding
    0.10
    upert
    0.09
     altogether
    0.09
     purposely
    0.09
     kicking
    0.09
    oller
    0.09
    DDL
    0.09
    ,—
    0.09
    enz
    0.09
    asil
    0.09
    Activations Density 0.258%

    No Known Activations