© 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. 30312
    Prev
    Next
    INDEX
    Explanations

    as

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     comps
    -0.08
     shar
    -0.08
    ils
    -0.08
    ilk
    -0.08
     Lub
    -0.08
     Pearce
    -0.08
     Lau
    -0.08
     saints
    -0.08
     sworn
    -0.07
    trag
    -0.07
    POSITIVE LOGITS
    ante
    0.11
     wave
    0.10
     strands
    0.10
    hoc
    0.10
    Paths
    0.10
    Recognition
    0.10
    ipop
    0.09
    .files
    0.09
    kus
    0.09
     Wave
    0.09
    Activations Density 0.017%

    No Known Activations