© 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. 116631
    Prev
    Next
    INDEX
    Explanations

    design, shape, creative, education

    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
     campaigners
    -0.09
     con
    -0.09
     cracking
    -0.08
     cracked
    -0.08
     Hamburg
    -0.08
     glands
    -0.08
    -da
    -0.08
     Lub
    -0.08
    aho
    -0.08
     Zig
    -0.08
    POSITIVE LOGITS
     decis
    0.12
    adan
    0.10
    /AP
    0.09
     pts
    0.09
     tl
    0.09
     Chandler
    0.09
    ören
    0.09
    /P
    0.09
     Fot
    0.09
     Heck
    0.09
    Activations Density 0.001%

    No Known Activations