© 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. 27558
    Prev
    Next
    INDEX
    Explanations

    season or cycle

    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
     powerless
    -0.13
     Bearing
    -0.12
    ibo
    -0.12
     Recall
    -0.11
     une
    -0.11
     Unc
    -0.11
    irm
    -0.11
     irresistible
    -0.11
     uncomfort
    -0.11
    orns
    -0.10
    POSITIVE LOGITS
     genuinely
    0.10
     alongside
    0.09
    /ng
    0.09
     triumph
    0.08
     genuine
    0.08
     satisfied
    0.08
    ayo
    0.08
     matched
    0.08
     stake
    0.08
     legit
    0.08
    Activations Density 0.008%

    No Known Activations