© 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. 117115
    Prev
    Next
    INDEX
    Explanations

    you can 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
     Deutsch
    -0.10
    ieron
    -0.10
    zik
    -0.10
    ichel
    -0.09
    ery
    -0.09
    gray
    -0.09
    ivent
    -0.09
     relaxing
    -0.09
    pur
    -0.09
    wg
    -0.09
    POSITIVE LOGITS
     bet
    0.28
     assured
    0.25
     rest
    0.22
     assure
    0.21
     sure
    0.19
     guaranteed
    0.18
     guarantee
    0.18
     assures
    0.17
     assurance
    0.17
     Bet
    0.17
    Activations Density 0.060%

    No Known Activations