© 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. 50159
    Prev
    Next
    INDEX
    Explanations

    fabrics and patterns

    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
    cis
    -0.13
    erton
    -0.12
     Kimber
    -0.12
     jugg
    -0.11
    -ves
    -0.10
    Ars
    -0.10
    ichert
    -0.10
     Bain
    -0.10
     circumcision
    -0.10
     Shutdown
    -0.09
    POSITIVE LOGITS
     fabric
    0.10
     sheets
    0.09
     suitable
    0.09
     sheet
    0.09
     desired
    0.09
     zab
    0.09
     useful
    0.09
     usable
    0.08
    sheet
    0.08
     Hak
    0.08
    Activations Density 0.001%

    No Known Activations