© 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. 27637
    Prev
    Next
    INDEX
    Explanations

    heart or root

    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
     Heb
    -0.14
    gps
    -0.11
    GPS
    -0.11
     Buccane
    -0.11
    iah
    -0.10
     Flames
    -0.10
     Reviewed
    -0.10
    atur
    -0.10
    733
    -0.10
    iez
    -0.10
    POSITIVE LOGITS
    -center
    0.08
     fo
    0.08
     redund
    0.08
     central
    0.07
     suburb
    0.07
     shelter
    0.07
     rearr
    0.07
     coroutine
    0.06
    bra
    0.06
     resides
    0.06
    Activations Density 0.001%

    No Known Activations