© 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. 91945
    Prev
    Next
    INDEX
    Explanations

    pledged to serve

    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
     promise
    -0.21
     promises
    -0.17
     Promise
    -0.17
     promised
    -0.16
    promise
    -0.15
     assurances
    -0.13
     guarantee
    -0.13
     guarantees
    -0.12
     Guarantee
    -0.12
     guar
    -0.11
    POSITIVE LOGITS
     NEVER
    0.11
    yas
    0.11
    never
    0.10
     never
    0.10
     Johnston
    0.10
     WON
    0.09
    DSP
    0.09
     NEW
    0.09
    uer
    0.09
    elter
    0.09
    Activations Density 0.043%

    No Known Activations