© 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. 28621
    Prev
    Next
    INDEX
    Explanations

    discussion of related art

    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
    ativ
    -0.10
    uka
    -0.09
     Morris
    -0.09
     ken
    -0.09
     Vega
    -0.09
     Ken
    -0.09
     allot
    -0.08
     Mack
    -0.08
     IMM
    -0.08
     Sund
    -0.08
    POSITIVE LOGITS
    forge
    0.10
    arel
    0.10
     rot
    0.09
    erm
    0.09
     recip
    0.09
     reciprocal
    0.09
     Duo
    0.09
    supports
    0.09
     scroll
    0.09
    ucer
    0.09
    Activations Density 0.003%

    No Known Activations