© 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. 49544
    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
    remen
    -0.10
    ewe
    -0.10
    795
    -0.09
    onen
    -0.09
    Outlined
    -0.09
     esl
    -0.09
    Ĺı
    -0.09
    ffi
    -0.09
     nok
    -0.09
     Owned
    -0.08
    POSITIVE LOGITS
    dana
    0.09
     pec
    0.09
    adf
    0.09
    modification
    0.08
     unlaw
    0.08
     Pars
    0.08
     Burlington
    0.08
     Trinity
    0.08
    uis
    0.08
     Concord
    0.08
    Activations Density 0.000%

    No Known Activations