© 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. 91442
    Prev
    Next
    INDEX
    Explanations

    `.<p>I`

    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
     Featured
    -0.10
    itor
    -0.10
    asty
    -0.09
    arkan
    -0.09
     fung
    -0.09
    /rem
    -0.09
     Bren
    -0.09
     alg
    -0.09
    dat
    -0.09
    una
    -0.09
    POSITIVE LOGITS
    uhl
    0.08
    ør
    0.08
    mil
    0.08
     reproduced
    0.08
     mildly
    0.08
     Sur
    0.08
     Ord
    0.08
    elow
    0.08
    arda
    0.07
     Needless
    0.07
    Activations Density 0.043%

    No Known Activations