© 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. 6428
    Prev
    Next
    INDEX
    Explanations

    stabl

    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
     whip
    -0.11
     wreck
    -0.10
    ductive
    -0.10
    821
    -0.09
    lays
    -0.09
    enance
    -0.09
     Renaissance
    -0.09
    erior
    -0.09
    .apple
    -0.09
    erver
    -0.09
    POSITIVE LOGITS
     stal
    0.16
     sta
    0.12
     Stable
    0.12
     stable
    0.11
    meeting
    0.10
    ioned
    0.10
    flation
    0.10
     steadfast
    0.10
    stable
    0.10
     stability
    0.09
    Activations Density 0.053%

    No Known Activations