© 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. 116959
    Prev
    Next
    INDEX
    Explanations

    appointed by

    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
     conservatism
    -0.09
     Accepted
    -0.09
     official
    -0.09
     Auditor
    -0.09
     reporters
    -0.09
    dcc
    -0.09
     incest
    -0.08
     aup
    -0.08
     Witnesses
    -0.08
     vulner
    -0.08
    POSITIVE LOGITS
     generous
    0.13
     friends
    0.13
     parents
    0.12
     sympathetic
    0.12
     concerned
    0.12
     philanth
    0.11
     prank
    0.11
     grateful
    0.11
     friend
    0.11
     industri
    0.11
    Activations Density 0.396%

    No Known Activations