© 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. 48501
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs

    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
     Wer
    -0.09
     Asi
    -0.09
     hugs
    -0.08
    hel
    -0.08
    979
    -0.08
     electronic
    -0.08
     litt
    -0.08
    wer
    -0.08
     noticeably
    -0.08
    Wer
    -0.07
    POSITIVE LOGITS
     wish
    0.14
     heard
    0.12
     Heard
    0.12
     accidentally
    0.11
     bet
    0.11
     prefer
    0.11
     met
    0.11
    kr
    0.11
     boredom
    0.10
    RL
    0.10
    Activations Density 0.010%

    No Known Activations