© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    end of sentence or quotation

    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
     expos
    -0.07
    ċ
    -0.07
    ityEngine
    -0.07
     expo
    -0.06
     Stam
    -0.06
    łéĻ¤
    -0.06
    (QL
    -0.06
    (KP
    -0.06
    ÃŁen
    -0.06
     Spar
    -0.06
    POSITIVE LOGITS
    aur
    0.13
    ucci
    0.11
     Gig
    0.11
    ettle
    0.11
    usch
    0.11
    uj
    0.11
    aylor
    0.11
    (...)↵
    0.11
    udden
    0.11
    enny
    0.11
    Activations Density 0.418%

    No Known Activations