© 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. 15265
    Prev
    Next
    INDEX
    Explanations

    AS IS clause or file paths

    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
     Bek
    -0.09
    bek
    -0.09
     nomin
    -0.09
     subs
    -0.08
     separately
    -0.08
    leon
    -0.08
    ungen
    -0.07
     sang
    -0.07
     Mayer
    -0.07
    lesen
    -0.07
    POSITIVE LOGITS
     sais
    0.11
     Ange
    0.10
    zp
    0.10
    oman
    0.10
     Reserved
    0.10
     Tie
    0.10
    jr
    0.09
     specialties
    0.09
    mue
    0.09
     rue
    0.09
    Activations Density 0.001%

    No Known Activations