© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5164
    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
    -adjust
    -0.09
     displ
    -0.09
     entertain
    -0.09
    ãĥĭ
    -0.09
     suicide
    -0.09
     Empire
    -0.09
     Hazard
    -0.08
    stro
    -0.08
    pw
    -0.08
    Doctrine
    -0.08
    POSITIVE LOGITS
     whispers
    0.11
    (er
    0.09
     former
    0.09
     excursion
    0.09
     elegance
    0.09
     pals
    0.08
     exhib
    0.08
    IDD
    0.08
    Inline
    0.08
     appar
    0.08
    Activations Density 0.000%

    No Known Activations