© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117602
    Prev
    Next
    INDEX
    Explanations

    searched for

    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
    Negative Logits
     nond
    -0.11
     Shea
    -0.10
     lacked
    -0.10
     succ
    -0.10
     sug
    -0.10
    eb
    -0.10
     confess
    -0.10
    å¸ĥ
    -0.10
    اس
    -0.10
    ksam
    -0.10
    POSITIVE LOGITS
    ucha
    0.08
    ignon
    0.07
     Pavel
    0.07
     vet
    0.07
     Catal
    0.07
     Esk
    0.07
     Metal
    0.07
     metal
    0.07
     narrower
    0.07
     Campo
    0.07
    Activations Density 0.001%

    No Known Activations