© 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. 89934
    Prev
    Next
    INDEX
    Explanations

    promises better outcomes

    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
    alis
    -0.11
     proposition
    -0.11
    oris
    -0.10
    .AI
    -0.10
    ape
    -0.10
    OMB
    -0.10
    oad
    -0.09
    into
    -0.09
    alle
    -0.09
    browse
    -0.09
    POSITIVE LOGITS
     to
    0.13
    entially
    0.11
     assistance
    0.10
     surprises
    0.09
     sÄĥ
    0.09
     lots
    0.09
    ly
    0.09
     us
    0.09
     increased
    0.09
    /th
    0.08
    Activations Density 0.022%

    No Known Activations