© 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. 112283
    Prev
    Next
    INDEX
    Explanations

    fine, pattern, works, exactly

    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
     Burton
    -0.10
     Hoch
    -0.09
     parallels
    -0.09
     undis
    -0.08
    oop
    -0.08
     counterpart
    -0.08
     Blair
    -0.08
     Klo
    -0.08
    OSC
    -0.08
    ug
    -0.08
    POSITIVE LOGITS
     doubly
    0.16
     definitely
    0.13
     heck
    0.12
     likewise
    0.12
     certainly
    0.12
     Dit
    0.12
     dit
    0.11
     slightly
    0.11
     even
    0.11
     DEFIN
    0.11
    Activations Density 0.207%

    No Known Activations