© 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. 114318
    Prev
    Next
    INDEX
    Explanations

    maps, trips, institutions, weapons, reactions, pigs, sharks, players

    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
     whose
    -0.21
     коÑĤоÑĢÑĭй
    -0.19
     which
    -0.18
    whose
    -0.18
     that
    -0.17
     who
    -0.16
     коÑĤоÑĢ
    -0.13
    that
    -0.13
    which
    -0.13
    who
    -0.12
    POSITIVE LOGITS
     contender
    0.13
     Schwarz
    0.10
     wann
    0.10
    spiel
    0.09
     ours
    0.09
    oub
    0.09
     viable
    0.09
    liner
    0.09
     despite
    0.09
    ikk
    0.08
    Activations Density 0.187%

    No Known Activations