© 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. 30216
    Prev
    Next
    INDEX
    Explanations

    cover his

    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
    jom
    -0.12
     Gur
    -0.10
    nat
    -0.10
     Meng
    -0.09
     Nancy
    -0.09
     lifting
    -0.09
    813
    -0.09
    annes
    -0.09
     Bru
    -0.09
    /man
    -0.09
    POSITIVE LOGITS
     Lind
    0.12
     except
    0.11
     rooted
    0.11
     coc
    0.11
     dormant
    0.10
    Except
    0.10
     callers
    0.09
    anks
    0.09
     conserv
    0.09
     floors
    0.09
    Activations Density 0.019%

    No Known Activations