© 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. 28214
    Prev
    Next
    INDEX
    Explanations

    license agreements

    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
     sequ
    -0.12
     here
    -0.11
     herein
    -0.11
    åij¨
    -0.10
     prepared
    -0.10
     ici
    -0.10
     painstaking
    -0.10
     HERE
    -0.10
    æŃ£åľ¨
    -0.09
     longstanding
    -0.09
    POSITIVE LOGITS
     encounter
    0.12
     glimps
    0.12
     glimpse
    0.12
     tomorrow
    0.11
     future
    0.10
     visit
    0.10
     incident
    0.10
    incident
    0.10
     touched
    0.09
     encountered
    0.09
    Activations Density 0.079%

    No Known Activations