© 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. 6112
    Prev
    Next
    INDEX
    Explanations

    INCORPORATED, substituting, puppeteer, javax.swing, http

    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
    olio
    -0.08
    ese
    -0.08
    ioso
    -0.08
    ingly
    -0.08
     —↵↵
    -0.07
     ling
    -0.07
    alles
    -0.07
    das
    -0.07
    IOS
    -0.07
    alled
    -0.07
    POSITIVE LOGITS
     Curtis
    0.11
     Encore
    0.10
     Pul
    0.10
    utable
    0.10
    lam
    0.10
     Curtain
    0.10
    Fault
    0.10
    Trait
    0.10
    ?p
    0.10
    ½æķ°
    0.09
    Activations Density 0.001%

    No Known Activations