© 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. 28010
    Prev
    Next
    INDEX
    Explanations

    riveting, riviera, Riverview, rivaroxaban, Rivest

    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
     nond
    -0.08
     extingu
    -0.08
    aba
    -0.08
    ator
    -0.07
     stro
    -0.07
    aque
    -0.07
    ATE
    -0.07
    hue
    -0.07
     spr
    -0.07
     relativ
    -0.07
    POSITIVE LOGITS
    alling
    0.15
     riv
    0.15
     Riv
    0.13
     ming
    0.12
     Favorites
    0.11
    afb
    0.11
    iera
    0.11
    ä»ĺ
    0.11
    ivals
    0.10
    ingly
    0.10
    Activations Density 0.002%

    No Known Activations