© 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. 90019
    Prev
    Next
    INDEX
    Explanations

    to support or request

    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
     Germ
    -0.10
    !!)↵
    -0.08
    (Link
    -0.08
    /place
    -0.08
    reas
    -0.08
     indeb
    -0.08
    alu
    -0.08
     Radical
    -0.08
    NEL
    -0.08
     Mahmoud
    -0.08
    POSITIVE LOGITS
    [];č↵
    0.09
     symlink
    0.09
    unread
    0.08
    fav
    0.08
    reopen
    0.08
     notably
    0.08
    apel
    0.08
     Alb
    0.08
    dispose
    0.08
    icorn
    0.08
    Activations Density 0.470%

    No Known Activations