© 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. 46541
    Prev
    Next
    INDEX
    Explanations

    top, prime, tops

    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
     polarization
    -0.10
     Metallic
    -0.10
    vie
    -0.09
     Vik
    -0.09
     polls
    -0.09
     Budd
    -0.09
    /from
    -0.09
     fridge
    -0.09
    ilik
    -0.08
     freezer
    -0.08
    POSITIVE LOGITS
    /oauth
    0.12
     ten
    0.10
    loys
    0.10
    cip
    0.09
     tops
    0.09
     hoax
    0.09
     providers
    0.09
    /design
    0.09
     Leading
    0.09
     trous
    0.09
    Activations Density 0.001%

    No Known Activations