© 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. 111397
    Prev
    Next
    INDEX
    Explanations

    sin

    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
     recursive
    -0.09
     stun
    -0.08
     decrypted
    -0.08
    stick
    -0.08
     haz
    -0.08
    idor
    -0.08
    bab
    -0.08
     civilized
    -0.08
    tsy
    -0.08
     qualifiers
    -0.08
    POSITIVE LOGITS
     sin
    0.26
     Sin
    0.24
    .Sin
    0.24
    Sin
    0.23
    .sin
    0.22
     sinful
    0.21
     SIN
    0.21
     sins
    0.21
    (sin
    0.21
    _sin
    0.21
    Activations Density 0.138%

    No Known Activations