© 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. 16500
    Prev
    Next
    INDEX
    Explanations

    affiliates

    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
     rag
    -0.10
     po
    -0.10
    odial
    -0.10
    eson
    -0.09
     Ronald
    -0.09
     dul
    -0.09
     Lancaster
    -0.09
     Bord
    -0.09
     Zum
    -0.09
    esto
    -0.09
    POSITIVE LOGITS
     whichever
    0.26
     depending
    0.22
    depending
    0.20
     respectively
    0.13
    ients
    0.13
    -wh
    0.13
     Depending
    0.12
     thereof
    0.12
    pter
    0.12
    wh
    0.12
    Activations Density 1.308%

    No Known Activations