© 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. 33262
    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
     cour
    -0.07
     Belle
    -0.07
    aea
    -0.07
     CIS
    -0.07
    .cf
    -0.07
     Lal
    -0.06
    isoft
    -0.06
     PF
    -0.06
     erratic
    -0.06
     Floyd
    -0.06
    POSITIVE LOGITS
     grate
    0.12
    oppable
    0.12
    acci
    0.12
    èIJ
    0.11
     diploma
    0.11
     overst
    0.11
    -summary
    0.11
     Cree
    0.11
    ODULE
    0.11
     cooler
    0.11
    Activations Density 0.000%

    No Known Activations