© 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. 89559
    Prev
    Next
    INDEX
    Explanations

    closing remarks

    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
    .dep
    -0.10
    ãĢģãĢģ
    -0.09
     surrounding
    -0.09
     CPS
    -0.09
    ,in
    -0.09
     recalled
    -0.09
    bla
    -0.09
    immel
    -0.08
    |int
    -0.08
    -------------</
    -0.08
    POSITIVE LOGITS
     Kiss
    0.12
     kisses
    0.10
    ↵↵
    0.10
    enas
    0.09
     Lis
    0.09
    ixo
    0.09
     kiss
    0.09
    unto
    0.08
     hoped
    0.08
     regards
    0.08
    Activations Density 0.016%

    No Known Activations