© 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. 89372
    Prev
    Next
    INDEX
    Explanations

    citation contexts

    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
     upstairs
    -0.11
     permanently
    -0.11
    ivi
    -0.11
    vey
    -0.10
    BD
    -0.10
    lik
    -0.10
    jur
    -0.10
     jal
    -0.10
     ici
    -0.09
    918
    -0.09
    POSITIVE LOGITS
     alongside
    0.12
     lors
    0.10
     whenever
    0.10
     disproportionately
    0.10
     when
    0.10
     during
    0.09
     repeatedly
    0.09
     even
    0.09
     disproportionate
    0.09
     CAS
    0.09
    Activations Density 0.565%

    No Known Activations