© 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. 89206
    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
     Broadcasting
    -0.09
    emb
    -0.09
    adam
    -0.09
    oun
    -0.09
     altogether
    -0.08
     Petty
    -0.08
     sworn
    -0.08
    º«
    -0.07
     Bernstein
    -0.07
    olle
    -0.07
    POSITIVE LOGITS
    uve
    0.10
     Wag
    0.10
    bi
    0.10
     Crom
    0.10
     voyeur
    0.09
     Idle
    0.09
     Prote
    0.09
    culus
    0.09
    -insert
    0.09
     Ps
    0.09
    Activations Density 0.000%

    No Known Activations