© 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. 29019
    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
     Tro
    -0.09
    nement
    -0.08
    iy
    -0.08
    åİ
    -0.07
    ilen
    -0.07
    tron
    -0.07
    walker
    -0.07
    ilty
    -0.07
     Lim
    -0.07
     chan
    -0.07
    POSITIVE LOGITS
     lash
    0.11
     Outstanding
    0.11
    897
    0.11
     Fischer
    0.11
     powering
    0.11
    zl
    0.10
     outstanding
    0.10
     XP
    0.10
    pras
    0.10
    kul
    0.10
    Activations Density 0.000%

    No Known Activations