© 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. 27461
    Prev
    Next
    INDEX
    Explanations

    on, auf, på

    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
    lage
    -0.11
    -framework
    -0.11
     Bes
    -0.10
    asar
    -0.10
    209
    -0.10
     regrets
    -0.10
    otron
    -0.09
     Yo
    -0.09
     threads
    -0.09
    Bes
    -0.09
    POSITIVE LOGITS
    Meet
    0.11
     expense
    0.10
    hee
    0.10
     level
    0.10
     loft
    0.10
    recht
    0.09
     forefront
    0.09
    Begin
    0.09
     manner
    0.09
     places
    0.09
    Activations Density 0.179%

    No Known Activations