© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48344
    Prev
    Next
    INDEX
    Explanations

    cheapest, free, singly

    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
     spit
    -0.09
    oho
    -0.08
     Handy
    -0.08
    .about
    -0.08
     proclaimed
    -0.07
    Idle
    -0.07
    Reserved
    -0.07
    _about
    -0.07
     pis
    -0.07
    Ìģ
    -0.07
    POSITIVE LOGITS
     Hess
    0.10
     bang
    0.10
     Salv
    0.10
     singly
    0.10
    kek
    0.10
     cheapest
    0.10
     free
    0.10
     salv
    0.10
     deriv
    0.10
     Dew
    0.10
    Activations Density 0.013%

    No Known Activations