© 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. 112782
    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
     Va
    -0.13
    iani
    -0.11
    Compat
    -0.11
    prov
    -0.10
     pars
    -0.10
    odos
    -0.10
     Dud
    -0.10
     konk
    -0.10
    åı¸
    -0.10
     defer
    -0.10
    POSITIVE LOGITS
     elev
    0.08
     flyer
    0.08
     smiling
    0.08
    .face
    0.08
    aleigh
    0.07
    .pref
    0.07
     breakout
    0.07
    after
    0.07
     gradu
    0.07
    gor
    0.07
    Activations Density 0.000%

    No Known Activations