© 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. 33318
    Prev
    Next
    INDEX
    Explanations

    OK, accept, dismiss, confirm actions

    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
     fav
    -0.12
    fy
    -0.11
     favoured
    -0.11
    isa
    -0.10
    deleted
    -0.10
    reta
    -0.10
    fav
    -0.10
    isen
    -0.10
     favors
    -0.10
     Pearce
    -0.10
    POSITIVE LOGITS
     OK
    0.21
     accept
    0.20
     Accept
    0.19
     dismiss
    0.19
     ok
    0.18
    OK
    0.18
     Continue
    0.18
     Confirm
    0.17
     confirm
    0.17
     Proceed
    0.17
    Activations Density 0.359%

    No Known Activations