© 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. 91154
    Prev
    Next
    INDEX
    Explanations

    invention of

    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
    à¸
    -0.12
     illum
    -0.11
     ambassadors
    -0.11
    pto
    -0.11
    elay
    -0.10
    iska
    -0.10
    sville
    -0.10
     rpt
    -0.10
    ë¹Ħ
    -0.10
    ’est
    -0.10
    POSITIVE LOGITS
    asl
    0.10
    oki
    0.08
     scorer
    0.08
     Nowadays
    0.08
     Pax
    0.08
     Sight
    0.07
     recently
    0.07
     famously
    0.07
    alc
    0.07
     program
    0.07
    Activations Density 0.007%

    No Known Activations