© 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. 5426
    Prev
    Next
    INDEX
    Explanations

    in a

    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
    Abr
    -0.11
    ynes
    -0.09
    bia
    -0.09
     Soap
    -0.09
     eyebrow
    -0.09
    itest
    -0.08
     stir
    -0.08
     Chancellor
    -0.08
     Barry
    -0.08
    used
    -0.08
    POSITIVE LOGITS
     kissed
    0.11
     Roth
    0.09
     first
    0.09
    iedo
    0.09
    ket
    0.08
     PIT
    0.08
     Morrow
    0.08
     Pis
    0.08
    abcdefghijklmnop
    0.08
    alu
    0.08
    Activations Density 0.034%

    No Known Activations