© 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. 49626
    Prev
    Next
    INDEX
    Explanations

    promise, assure, guarantee

    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
    rene
    -0.12
    enberg
    -0.09
    ief
    -0.09
     rationale
    -0.09
    sted
    -0.09
    -fi
    -0.08
    ailles
    -0.08
    udo
    -0.08
     Rud
    -0.08
     Gould
    -0.08
    POSITIVE LOGITS
     guarantee
    0.19
     assure
    0.18
     guaranteed
    0.16
     Guarantee
    0.15
     guar
    0.15
     assures
    0.15
     promise
    0.15
     guarantees
    0.15
     Guaranteed
    0.14
     assured
    0.14
    Activations Density 0.017%

    No Known Activations