© 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. 32333
    Prev
    Next
    INDEX
    Explanations

    enlargement or shrinking

    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
    omp
    -0.10
     nursery
    -0.08
    edy
    -0.08
    andard
    -0.07
    ardy
    -0.07
     Roberto
    -0.07
     breathing
    -0.07
    late
    -0.07
    issing
    -0.07
     Bam
    -0.07
    POSITIVE LOGITS
     enlargement
    0.15
    -quote
    0.12
     pills
    0.12
    -pills
    0.12
     shrinking
    0.11
    oren
    0.11
    gra
    0.11
    ÑĢг
    0.11
     organ
    0.11
     bpp
    0.11
    Activations Density 0.019%

    No Known Activations