© 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. 91085
    Prev
    Next
    INDEX
    Explanations

    not at all

    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
     stricter
    -0.09
     WS
    -0.09
     sheer
    -0.09
     unmist
    -0.09
    еÑģÑĤи
    -0.09
     utterly
    -0.09
     downright
    -0.09
    .dsl
    -0.09
     arity
    -0.09
     arguably
    -0.09
    POSITIVE LOGITS
     surprised
    0.12
     diss
    0.11
     interested
    0.11
     like
    0.10
     Clar
    0.10
     present
    0.10
     resembling
    0.10
     Guaranteed
    0.09
     guarantee
    0.09
     meant
    0.09
    Activations Density 0.012%

    No Known Activations