© 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. 113867
    Prev
    Next
    INDEX
    Explanations

    eee, aaaa, ooo

    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
    asca
    -0.08
     dis
    -0.08
    asy
    -0.08
    à¹Į
    -0.08
    -less
    -0.08
     explicit
    -0.08
    indre
    -0.08
     affinity
    -0.07
     assum
    -0.07
     elong
    -0.07
    POSITIVE LOGITS
    ief
    0.11
     è¾ĵ
    0.11
     nouve
    0.10
     ($.
    0.10
    leigh
    0.10
     Chronicle
    0.10
    cola
    0.10
    trash
    0.09
     NoSuch
    0.09
    olars
    0.09
    Activations Density 0.071%

    No Known Activations