© 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. 5087
    Prev
    Next
    INDEX
    Explanations

    searching for potential candidates

    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
     sincer
    -0.10
    folios
    -0.09
     sincerity
    -0.09
    ayo
    -0.09
    osit
    -0.09
     Sed
    -0.09
     balk
    -0.09
     fle
    -0.09
     mainstream
    -0.09
    fad
    -0.09
    POSITIVE LOGITS
     potential
    0.17
     suitable
    0.14
     candidates
    0.14
     prey
    0.14
     willing
    0.14
     new
    0.13
     opportunities
    0.13
     prospective
    0.13
     interesting
    0.12
     collaborators
    0.12
    Activations Density 0.031%

    No Known Activations