© 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. 6675
    Prev
    Next
    INDEX
    Explanations

    blessing or blessed

    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
     earliest
    -0.08
    uckle
    -0.08
     Woo
    -0.08
    azzi
    -0.08
    ashi
    -0.08
     sucess
    -0.08
     Hue
    -0.08
    olk
    -0.08
     tip
    -0.08
    (Image
    -0.07
    POSITIVE LOGITS
    edly
    0.19
    eds
    0.13
    fully
    0.13
     bestowed
    0.12
    ington
    0.12
     Relief
    0.12
     abund
    0.11
    esen
    0.11
    phem
    0.11
     abound
    0.11
    Activations Density 0.007%

    No Known Activations