© 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. 33604
    Prev
    Next
    INDEX
    Explanations

    blobs, blooper, bloody, blooming, blooms, blochii

    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
    mut
    -0.10
    alto
    -0.10
    agnet
    -0.09
    gar
    -0.09
    mie
    -0.09
    reck
    -0.09
    plain
    -0.09
    oret
    -0.09
    erna
    -0.09
    mid
    -0.09
    POSITIVE LOGITS
     Blo
    0.11
    blo
    0.10
    isters
    0.10
    Blo
    0.09
     Lob
    0.09
    Oi
    0.09
    Us
    0.09
     Winds
    0.09
    AIR
    0.09
    hev
    0.08
    Activations Density 0.002%

    No Known Activations