© 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. 30601
    Prev
    Next
    INDEX
    Explanations

    suspected, claimed, identified, known, convicted

    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
     Parliamentary
    -0.10
    umm
    -0.10
     ime
    -0.10
    eker
    -0.10
     womens
    -0.09
    usty
    -0.09
    jan
    -0.09
    um
    -0.09
    QUEST
    -0.09
    uter
    -0.08
    POSITIVE LOGITS
     liar
    0.14
     slugg
    0.14
     devote
    0.14
     skeptic
    0.14
     addicts
    0.13
     optim
    0.13
     plagiar
    0.12
     pessim
    0.12
     criminals
    0.12
     achie
    0.12
    Activations Density 0.181%

    No Known Activations