© 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. 32653
    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
     Aub
    -0.09
    wel
    -0.09
     perch
    -0.08
     Victory
    -0.08
    elic
    -0.08
     haunt
    -0.08
     ledge
    -0.07
     Wel
    -0.07
     assail
    -0.07
    wers
    -0.07
    POSITIVE LOGITS
     Chatt
    0.12
     Gon
    0.11
    FOUND
    0.11
     incess
    0.11
    Geom
    0.11
     ban
    0.10
     cerca
    0.10
    igne
    0.10
     CIS
    0.10
     ISS
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.