© 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. 29041
    Prev
    Next
    INDEX
    Explanations

    code separators and comments

    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
    eton
    -0.10
    emen
    -0.08
    estroy
    -0.08
    finally
    -0.08
    kr
    -0.08
    .nav
    -0.08
    opot
    -0.08
     colle
    -0.08
    zn
    -0.08
    indr
    -0.08
    POSITIVE LOGITS
     Miche
    0.11
     Barker
    0.10
     Bere
    0.10
    <?↵
    0.09
     buck
    0.09
    clare
    0.09
     Pres
    0.09
     usu
    0.09
    ¡°
    0.09
     trou
    0.09
    Activations Density 0.011%

    No Known Activations