© 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. 50176
    Prev
    Next
    INDEX
    Explanations

    are permitted or persons to

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ullo
    -0.10
    anel
    -0.10
     nou
    -0.10
    nees
    -0.10
    REC
    -0.10
    FFT
    -0.10
    upal
    -0.09
     Protocol
    -0.09
    rupted
    -0.09
     Relations
    -0.09
    POSITIVE LOGITS
    RAD
    0.09
     af
    0.09
    vide
    0.09
     luc
    0.08
     equilibrium
    0.08
     Wallace
    0.08
     Leopard
    0.08
     nag
    0.08
     conta
    0.08
     Toe
    0.07
    Activations Density 0.001%

    No Known Activations