© 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. 6642
    Prev
    Next
    INDEX
    Explanations

    conducive or favorable conditions

    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
     Kos
    -0.12
     Buckley
    -0.11
    iten
    -0.11
     Tested
    -0.10
     alb
    -0.10
     outweigh
    -0.10
    borg
    -0.10
    ENN
    -0.10
     Spar
    -0.10
     Accepted
    -0.10
    POSITIVE LOGITS
     conducive
    0.53
     favorable
    0.24
     suited
    0.24
     suitable
    0.24
     facilitating
    0.23
     fertile
    0.23
     facilitates
    0.22
     suitability
    0.22
     facilitate
    0.21
     conduc
    0.21
    Activations Density 0.485%

    No Known Activations