© 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. 49476
    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
     blowing
    -0.08
    omi
    -0.08
     blows
    -0.08
    agen
    -0.08
     Warwick
    -0.08
     sen
    -0.07
     epis
    -0.07
     Lime
    -0.07
    iden
    -0.07
     LEG
    -0.07
    POSITIVE LOGITS
    HING
    0.11
     consc
    0.11
     Isl
    0.11
    stairs
    0.11
     NTN
    0.10
     spin
    0.10
    igu
    0.10
    /Dk
    0.10
    adge
    0.10
    inherits
    0.10
    Activations Density 0.000%

    No Known Activations