© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48972
    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
     seper
    -0.08
    baugh
    -0.08
    wk
    -0.08
     Directorate
    -0.08
     iff
    -0.08
    scr
    -0.08
    iros
    -0.07
     scr
    -0.07
    legate
    -0.07
    andom
    -0.07
    POSITIVE LOGITS
     Frid
    0.10
    ddl
    0.10
    oli
    0.10
     lick
    0.10
     Chad
    0.10
     ruth
    0.10
     extrav
    0.10
    _ov
    0.09
    ylan
    0.09
     experi
    0.09
    Activations Density 0.000%

    No Known Activations