© 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. 28048
    Prev
    Next
    INDEX
    Explanations

    which has been

    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
     idi
    -0.11
     Suc
    -0.10
     Rational
    -0.10
    COPE
    -0.10
     Libraries
    -0.10
     materials
    -0.10
    nants
    -0.10
     fla
    -0.10
    yb
    -0.10
    acb
    -0.10
    POSITIVE LOGITS
     synth
    0.09
     famously
    0.09
     plays
    0.09
    Its
    0.08
     Its
    0.08
     Dys
    0.08
     synthetic
    0.08
     ple
    0.08
     dys
    0.08
     dub
    0.08
    Activations Density 1.424%

    No Known Activations