© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112325
    Prev
    Next
    INDEX
    Explanations

    take care of

    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
     Som
    -0.12
     Nay
    -0.11
    Neg
    -0.11
    ulan
    -0.11
     Jennings
    -0.11
    som
    -0.11
     virtue
    -0.11
    aside
    -0.11
     roller
    -0.11
    .{
    -0.11
    POSITIVE LOGITS
     problem
    0.11
     matter
    0.10
     Problem
    0.10
     matters
    0.10
     problems
    0.09
    éĹ®é¢ĺ
    0.09
    äºĭ
    0.09
    issues
    0.09
    Problem
    0.09
     pes
    0.09
    Activations Density 0.016%

    No Known Activations