© 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. 88940
    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
     tape
    -0.12
    Ãļ
    -0.11
     Tape
    -0.11
    amar
    -0.11
     unpl
    -0.11
    jour
    -0.11
     manners
    -0.11
     therap
    -0.11
    855
    -0.11
    tape
    -0.11
    POSITIVE LOGITS
     abruptly
    0.07
     gracefully
    0.07
    reve
    0.07
     Beh
    0.07
     recl
    0.07
     exp
    0.07
     Illum
    0.07
     Lit
    0.06
     Visual
    0.06
     reactive
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.