© 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. 89946
    Prev
    Next
    INDEX
    Explanations

    Thanks for

    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
     cong
    -0.12
    *sp
    -0.12
     cosa
    -0.11
     prt
    -0.11
    XL
    -0.11
     BAB
    -0.10
    -REAL
    -0.10
     (?,
    -0.10
     ÑĤек
    -0.10
    /Foundation
    -0.10
    POSITIVE LOGITS
     guys
    0.16
     everyone
    0.12
     @
    0.11
     Helpful
    0.10
     Guys
    0.10
     Everyone
    0.09
    521
    0.09
     both
    0.09
     gentlemen
    0.09
     Admin
    0.09
    Activations Density 0.028%

    No Known Activations