© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5374
    Prev
    Next
    INDEX
    Explanations

    to [action verb]

    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
     spor
    -0.10
     systematically
    -0.09
     unexpectedly
    -0.09
     reluctantly
    -0.09
     begr
    -0.09
     rig
    -0.08
     solitary
    -0.08
    inker
    -0.08
     intermitt
    -0.08
    reck
    -0.08
    POSITIVE LOGITS
     sounding
    0.16
     sounded
    0.13
     joke
    0.13
     Montgomery
    0.11
     sound
    0.11
     clarify
    0.11
     Diff
    0.11
     redeem
    0.11
     disp
    0.11
    sound
    0.11
    Activations Density 0.012%

    No Known Activations