© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    selling or absorbing

    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
    .pp
    -0.10
     Barton
    -0.09
     Burl
    -0.08
    iew
    -0.08
    reff
    -0.08
    dac
    -0.08
    /language
    -0.08
     THESE
    -0.08
    ód
    -0.08
    esen
    -0.08
    POSITIVE LOGITS
     thereof
    0.23
     them
    0.15
     it
    0.14
     ones
    0.13
    aren
    0.12
     Them
    0.10
    ç®
    0.10
    952
    0.09
    them
    0.09
    ald
    0.09
    Activations Density 1.072%

    No Known Activations