© 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. 115648
    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
    Abr
    -0.11
    accumulator
    -0.09
    opa
    -0.09
     batter
    -0.09
    hta
    -0.08
    uka
    -0.08
    telephone
    -0.08
     Heath
    -0.08
    adel
    -0.08
     horn
    -0.08
    POSITIVE LOGITS
    erek
    0.11
    /material
    0.10
    -material
    0.10
    _fil
    0.10
     precisely
    0.09
    .Forms
    0.09
    upy
    0.09
     Pare
    0.09
    ;';↵
    0.09
     profund
    0.09
    Activations Density 0.000%

    No Known Activations