© 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. 91960
    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
     Lift
    -0.09
     wards
    -0.09
     wounded
    -0.09
     Damen
    -0.08
    /items
    -0.08
     Moran
    -0.08
     reprodu
    -0.08
    imen
    -0.08
     trustworthy
    -0.08
     marque
    -0.08
    POSITIVE LOGITS
     Kes
    0.11
    apes
    0.10
    oller
    0.10
    .cb
    0.10
    izont
    0.10
     finger
    0.09
     Gree
    0.09
    apollo
    0.09
     stranger
    0.09
    igit
    0.09
    Activations Density 0.000%

    No Known Activations