© 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. 92155
    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
    antz
    -0.09
     pé
    -0.09
     nich
    -0.09
     Chance
    -0.08
    utan
    -0.08
     adept
    -0.08
    seat
    -0.08
    warm
    -0.08
     Fan
    -0.08
     amor
    -0.08
    POSITIVE LOGITS
     Marr
    0.10
    ucs
    0.10
    enthal
    0.09
    eti
    0.09
    afa
    0.09
    866
    0.09
     confronting
    0.09
    omat
    0.09
     blind
    0.09
    ilo
    0.09
    Activations Density 0.000%

    No Known Activations