© 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. 112311
    Prev
    Next
    INDEX
    Explanations

    risk comparison

    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
    qual
    -0.09
     conv
    -0.09
     qualitative
    -0.09
     inevitably
    -0.09
     circum
    -0.09
     Bran
    -0.08
     chronological
    -0.08
     Savannah
    -0.08
     Ronnie
    -0.08
     retrospect
    -0.08
    POSITIVE LOGITS
     slightly
    0.14
     twice
    0.14
     (+
    0.13
     Relative
    0.13
     disproportionately
    0.12
     nearly
    0.12
     surprisingly
    0.12
     unusually
    0.12
     (.
    0.12
     unlucky
    0.12
    Activations Density 0.862%

    No Known Activations