© 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. 33627
    Prev
    Next
    INDEX
    Explanations

    keep things going

    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
     emphas
    -0.10
     pry
    -0.10
     realised
    -0.10
     organisation
    -0.09
     util
    -0.09
     organised
    -0.09
     realise
    -0.09
     priv
    -0.09
     Merkel
    -0.09
     authorised
    -0.09
    POSITIVE LOGITS
     popping
    0.11
    .bio
    0.09
    iti
    0.09
    awai
    0.09
     Pot
    0.09
    iego
    0.09
    yw
    0.09
     Tob
    0.09
     parallel
    0.09
     Bake
    0.09
    Activations Density 0.024%

    No Known Activations