© 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. 91401
    Prev
    Next
    INDEX
    Explanations

    gaining prominence, understanding, knowledge, popularity

    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
     fetched
    -0.12
     retrieved
    -0.11
     Shiv
    -0.11
     obtained
    -0.11
     obten
    -0.11
     Bunny
    -0.11
    aler
    -0.10
     ëĤĺ
    -0.10
     elic
    -0.10
    vest
    -0.10
    POSITIVE LOGITS
     footh
    0.10
     traction
    0.08
     rapidly
    0.08
     aup
    0.08
     from
    0.08
     thru
    0.08
     fron
    0.08
     ire
    0.08
    æĺĵ
    0.08
     chops
    0.08
    Activations Density 0.275%

    No Known Activations