© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48348
    Prev
    Next
    INDEX
    Explanations

    enumerating points or lists

    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
    urable
    -0.08
    alen
    -0.08
     Äiji
    -0.07
     MacDonald
    -0.07
    aju
    -0.07
    .ssl
    -0.07
     glor
    -0.07
    erson
    -0.07
    /max
    -0.07
     Finally
    -0.07
    POSITIVE LOGITS
     suffice
    0.14
     Firstly
    0.14
     brace
    0.12
     Brace
    0.12
     Suff
    0.12
     First
    0.12
    First
    0.12
    æĺİ
    0.12
    esis
    0.12
     namely
    0.12
    Activations Density 0.568%

    No Known Activations