© 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. 31853
    Prev
    Next
    INDEX
    Explanations

    organ prolapse

    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
     vict
    -0.09
    arris
    -0.09
     reck
    -0.08
     cleared
    -0.08
    acio
    -0.08
     Til
    -0.08
    auc
    -0.08
     Opr
    -0.08
     lash
    -0.08
     Sadd
    -0.08
    POSITIVE LOGITS
     relocated
    0.15
     hanging
    0.14
     Hanging
    0.13
     Kore
    0.13
     dangling
    0.12
     misplaced
    0.12
     relocate
    0.12
     relocation
    0.12
     liqu
    0.12
     intest
    0.12
    Activations Density 0.054%

    No Known Activations