© 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. 111971
    Prev
    Next
    INDEX
    Explanations

    names starting with R/H prefixes

    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
     cep
    -0.10
     Singleton
    -0.10
    MEA
    -0.10
     goo
    -0.09
     prospect
    -0.09
     cum
    -0.09
     thicker
    -0.09
     effectively
    -0.09
     effective
    -0.09
     ineffective
    -0.09
    POSITIVE LOGITS
    emple
    0.10
     Undo
    0.09
     unl
    0.09
    hart
    0.09
    elow
    0.09
     Trou
    0.08
     trav
    0.08
    enant
    0.08
     conhe
    0.08
    enschaft
    0.08
    Activations Density 0.122%

    No Known Activations