© 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. 87739
    Prev
    Next
    INDEX
    Explanations

    intensifiers like very, really, too

    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
    aska
    -0.12
     Stam
    -0.10
     large
    -0.10
    edor
    -0.10
     Het
    -0.09
    IRO
    -0.09
     strongly
    -0.09
    hti
    -0.09
     heavy
    -0.09
     sharp
    -0.09
    POSITIVE LOGITS
     VERY
    0.28
    VERY
    0.25
     Very
    0.22
     TOO
    0.21
     REALLY
    0.21
    Very
    0.21
     very
    0.20
    very
    0.20
     Extremely
    0.18
     extremely
    0.17
    Activations Density 0.166%

    No Known Activations