© 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. 89285
    Prev
    Next
    INDEX
    Explanations

    names like Stacy, Hanson, Laurie

    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
    olio
    -0.09
    raj
    -0.09
     occasional
    -0.09
    /column
    -0.09
    arding
    -0.08
    utral
    -0.08
    esco
    -0.08
     Ober
    -0.08
    lake
    -0.08
    ermen
    -0.08
    POSITIVE LOGITS
    yg
    0.11
    ÑĤÑĮ
    0.10
    itated
    0.09
    âĸĪ
    0.09
    ynth
    0.09
    ynes
    0.09
    tion
    0.09
     sweetheart
    0.09
    yt
    0.09
    FUL
    0.09
    Activations Density 0.012%

    No Known Activations