© 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. 15888
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and equations

    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
    Âł
    -0.10
     reve
    -0.09
     Tex
    -0.09
    aci
    -0.08
     rever
    -0.08
    >čč↵
    -0.08
     &#
    -0.08
    %d
    -0.08
     blessed
    -0.08
    unds
    -0.08
    POSITIVE LOGITS
     vol
    0.10
     vib
    0.10
     Expanded
    0.10
     clandest
    0.09
     nearby
    0.09
     volunteer
    0.09
    —if
    0.09
     Vib
    0.09
    /js
    0.09
     quasi
    0.09
    Activations Density 0.009%

    No Known Activations