© 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. 15079
    Prev
    Next
    INDEX
    Explanations

    so-called / imaginary / infamous

    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
     vintage
    -0.09
     dolls
    -0.08
     craw
    -0.08
     evasion
    -0.08
    114
    -0.07
     #-
    -0.07
     ris
    -0.07
    lan
    -0.07
    avia
    -0.07
     Parm
    -0.07
    POSITIVE LOGITS
    ipping
    0.12
     carrot
    0.12
    /math
    0.11
     '
    0.10
     straw
    0.10
     ‘
    0.10
     '(
    0.10
     eyebrow
    0.10
    hic
    0.10
     Â
    0.10
    Activations Density 0.019%

    No Known Activations