© 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. 15039
    Prev
    Next
    INDEX
    Explanations

    different genes, treatments, cancers

    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
     sometime
    -0.09
     masc
    -0.09
    osal
    -0.09
    IPA
    -0.08
    predictions
    -0.08
    ustr
    -0.08
     Imag
    -0.08
     Scient
    -0.08
    (Call
    -0.08
     hacks
    -0.08
    POSITIVE LOGITS
    AE
    0.10
     Raymond
    0.09
     dall
    0.09
     woo
    0.09
     Knife
    0.09
     whe
    0.09
     knife
    0.09
    è¶
    0.09
    .thumb
    0.08
     dangling
    0.08
    Activations Density 0.129%

    No Known Activations