© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    technically, quasi, resembles, termed

    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
     Moss
    -0.10
     Vog
    -0.09
    Perm
    -0.09
     Polar
    -0.09
    sig
    -0.08
     Ginger
    -0.08
     Rossi
    -0.08
    uts
    -0.08
    ADDR
    -0.08
    adan
    -0.08
    POSITIVE LOGITS
     technically
    0.30
    称
    0.24
     pseudo
    0.23
     termed
    0.21
     quasi
    0.19
     resembles
    0.19
     isn
    0.19
     Techn
    0.19
     resembling
    0.18
     resembled
    0.18
    Activations Density 0.505%

    No Known Activations