© 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. 115043
    Prev
    Next
    INDEX
    Explanations

    either express or implied

    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
     hawk
    -0.09
     porcelain
    -0.09
     Sears
    -0.08
    iga
    -0.08
    impse
    -0.08
     gated
    -0.08
    -but
    -0.08
    filters
    -0.08
     mens
    -0.08
     dem
    -0.08
    POSITIVE LOGITS
    oug
    0.09
     Straw
    0.09
    /k
    0.09
    isters
    0.09
     dispose
    0.08
    lement
    0.08
    674
    0.08
     unilateral
    0.08
     excuses
    0.08
     Cha
    0.08
    Activations Density 0.010%

    No Known Activations