© 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. 26826
    Prev
    Next
    INDEX
    Explanations

    so-called phrases or quoted terms

    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
     truly
    -0.09
     overt
    -0.09
     SPDX
    -0.09
     sheer
    -0.09
     heter
    -0.09
    erton
    -0.09
    igua
    -0.08
    lit
    -0.08
    andi
    -0.08
    ipa
    -0.08
    POSITIVE LOGITS
     experts
    0.14
     professionals
    0.11
     friends
    0.10
    Friends
    0.10
    friends
    0.10
     helpful
    0.10
    ingen
    0.10
     specialists
    0.09
     Experts
    0.09
    ROTO
    0.09
    Activations Density 0.110%

    No Known Activations