© 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. 90020
    Prev
    Next
    INDEX
    Explanations

    numerous / multiple

    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
    bbe
    -0.12
    abouts
    -0.11
     respectively
    -0.11
    äºĽ
    -0.10
    pool
    -0.10
    ward
    -0.10
    /she
    -0.10
     various
    -0.10
    Extras
    -0.10
    buster
    -0.10
    POSITIVE LOGITS
     sclerosis
    0.20
     (>
    0.13
     occasions
    0.12
    -choice
    0.11
     overlapping
    0.11
     amounts
    0.11
     times
    0.10
     attempts
    0.09
     strands
    0.09
     rounds
    0.09
    Activations Density 0.074%

    No Known Activations