© 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. 46701
    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
    ouro
    -0.08
    rott
    -0.08
     kidnapping
    -0.08
     Raid
    -0.07
     bere
    -0.07
    izi
    -0.07
     if
    -0.07
     Roch
    -0.07
     cad
    -0.07
    Es
    -0.07
    POSITIVE LOGITS
    cripts
    0.10
     REGARD
    0.10
    strap
    0.09
    CLOSE
    0.09
    PLUS
    0.09
     collage
    0.09
     STR
    0.09
    olume
    0.09
    OfString
    0.09
    554
    0.09
    Activations Density 0.000%

    No Known Activations