© 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. 92023
    Prev
    Next
    INDEX
    Explanations

    contrasts and qualifications

    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
     unmarried
    -0.13
     nonzero
    -0.11
     unofficial
    -0.10
     unnatural
    -0.10
     imperfect
    -0.09
     disrespect
    -0.09
     uninterrupted
    -0.09
     unarmed
    -0.09
     monopol
    -0.09
     dislike
    -0.09
    POSITIVE LOGITS
     downright
    0.15
     outright
    0.14
     subtle
    0.12
     kits
    0.12
     pastoral
    0.12
     tender
    0.11
     playful
    0.11
    ASSERT
    0.11
     simply
    0.11
    opsy
    0.11
    Activations Density 0.079%

    No Known Activations