© 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. 17204
    Prev
    Next
    INDEX
    Explanations

    on a high/cloud/top

    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
    imi
    -0.11
    istro
    -0.10
    hem
    -0.10
     slowing
    -0.10
     wast
    -0.10
     twitch
    -0.09
     intimidating
    -0.09
     wasting
    -0.09
     earnest
    -0.09
     pul
    -0.09
    POSITIVE LOGITS
     highs
    0.33
     eup
    0.29
     lows
    0.23
     heights
    0.19
     exhilar
    0.18
     cloud
    0.18
     el
    0.18
     buoy
    0.18
     floated
    0.17
     bliss
    0.16
    Activations Density 0.074%

    No Known Activations