© 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. 115957
    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
     po
    -0.08
     h
    -0.08
     moss
    -0.07
     Respect
    -0.07
     Bent
    -0.06
     mo
    -0.06
     acts
    -0.06
     quizzes
    -0.06
    cline
    -0.06
     your
    -0.06
    POSITIVE LOGITS
    stab
    0.13
     Israelis
    0.12
    WER
    0.12
    anst
    0.12
    _rg
    0.11
    anh
    0.11
     Levine
    0.11
     KERNEL
    0.11
     Colombian
    0.11
    rel
    0.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.