© 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. 89065
    Prev
    Next
    INDEX
    Explanations

    KT17, SW7, 560012, 560, 080, 184, 173, 053, 735, 130, 55, 08092, 05393

    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
    iana
    -0.11
     Spotlight
    -0.10
     enlightened
    -0.10
     diligence
    -0.10
     diligently
    -0.10
     Bans
    -0.09
    MethodName
    -0.09
     up
    -0.09
     banana
    -0.09
    .override
    -0.09
    POSITIVE LOGITS
    $__
    0.09
     advant
    0.09
     benef
    0.08
    lator
    0.08
     handicap
    0.08
    /as
    0.07
     Imam
    0.07
     Postal
    0.07
     cog
    0.07
     slag
    0.07
    Activations Density 0.022%

    No Known Activations