© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    executed automatically

    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
     disput
    -0.13
     positively
    -0.12
     proudly
    -0.12
     boast
    -0.11
     brag
    -0.10
     abusive
    -0.10
     boasting
    -0.10
     boasted
    -0.10
     unde
    -0.10
     persu
    -0.10
    POSITIVE LOGITS
     sincerity
    0.19
     sincere
    0.19
     sincerely
    0.18
     apologized
    0.16
     apology
    0.14
     sincer
    0.14
     apologize
    0.14
     apologies
    0.14
     genuinely
    0.14
     polite
    0.13
    Activations Density 0.020%

    No Known Activations