© 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. 18451
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     subtraction
    -0.08
     chalk
    -0.08
     nitrogen
    -0.08
     Led
    -0.07
     Trou
    -0.07
     prematurely
    -0.07
     subtract
    -0.07
    (pref
    -0.07
    Sdk
    -0.07
     Subtract
    -0.07
    POSITIVE LOGITS
     Carp
    0.13
     seriously
    0.12
     prohibit
    0.11
     forbid
    0.11
    enser
    0.11
    inho
    0.11
    GEST
    0.11
    inar
    0.11
     Gest
    0.11
    yh
    0.10
    Activations Density 0.000%

    No Known Activations