© 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. 29197
    Prev
    Next
    INDEX
    Explanations

    email

    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
    trail
    -0.09
     agency
    -0.07
    olean
    -0.07
    trak
    -0.07
    chg
    -0.07
     diss
    -0.07
     Uploaded
    -0.07
     tok
    -0.07
    -category
    -0.07
    feld
    -0.07
    POSITIVE LOGITS
     Spare
    0.10
     defeats
    0.10
     Nicholson
    0.10
    elow
    0.10
    ensem
    0.10
     gigs
    0.10
    ..'
    0.10
    -at
    0.10
     bist
    0.10
     Swal
    0.10
    Activations Density 0.001%

    No Known Activations