© 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. 47698
    Prev
    Next
    INDEX
    Explanations

    belonging to or owned by a subject

    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
    isk
    -0.10
     Iss
    -0.09
    bid
    -0.08
    erto
    -0.08
    834
    -0.08
    nak
    -0.08
    thal
    -0.08
    atto
    -0.08
     Instant
    -0.07
    noon
    -0.07
    POSITIVE LOGITS
     traditionally
    0.11
     owned
    0.11
     belong
    0.11
     intend
    0.10
     deserve
    0.10
    ê³
    0.10
     belonged
    0.10
     phantom
    0.10
     Fav
    0.10
     owns
    0.10
    Activations Density 0.015%

    No Known Activations