© 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. 24964
    Prev
    Next
    INDEX
    Explanations

    gentle, soft, careful actions

    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
     hobby
    -0.13
     vacation
    -0.11
     summer
    -0.10
     parties
    -0.10
     parenting
    -0.10
     brag
    -0.10
     beef
    -0.10
     Idea
    -0.10
     someday
    -0.09
     champion
    -0.09
    POSITIVE LOGITS
     gently
    0.18
     techniques
    0.16
     gradually
    0.15
     gentle
    0.15
     softly
    0.14
     carefully
    0.13
     specially
    0.13
     Gent
    0.13
     gent
    0.13
     customized
    0.13
    Activations Density 0.062%

    No Known Activations