© 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. 27155
    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
     amsterdam
    -0.08
    icont
    -0.08
    auf
    -0.08
    HN
    -0.08
     Amsterdam
    -0.08
    atten
    -0.08
    elo
    -0.08
     erotica
    -0.08
     Stud
    -0.08
    æĢ
    -0.08
    POSITIVE LOGITS
    inke
    0.12
     multic
    0.10
    ante
    0.10
    isex
    0.10
     Sew
    0.10
     aspir
    0.09
     multid
    0.09
     Advoc
    0.09
     multip
    0.09
    aines
    0.09
    Activations Density 0.000%

    No Known Activations