© 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. 24960
    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
    Negative Logits
     contingent
    -0.09
     blind
    -0.08
     gre
    -0.08
     Maul
    -0.08
     Lange
    -0.08
     clone
    -0.08
     Cah
    -0.08
     bored
    -0.08
     reach
    -0.08
     Mut
    -0.08
    POSITIVE LOGITS
     Bliss
    0.12
     heights
    0.10
    elt
    0.10
     Boeh
    0.10
    kich
    0.10
     sint
    0.10
     Thur
    0.10
    tero
    0.09
    erval
    0.09
     embarrassment
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.