© 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. 115128
    Prev
    Next
    INDEX
    Explanations

    cav followed by ite, il, ium, erta, all, ens

    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
     Pep
    -0.10
     sacked
    -0.10
    ivia
    -0.10
    indow
    -0.10
    ece
    -0.10
    yards
    -0.10
    stead
    -0.10
    elist
    -0.10
    arth
    -0.10
     Thousand
    -0.10
    POSITIVE LOGITS
    alc
    0.17
     cav
    0.17
     Cav
    0.16
    uÅŁ
    0.10
     procession
    0.10
    illation
    0.09
     cavity
    0.09
     ench
    0.09
    ortex
    0.09
     Pear
    0.09
    Activations Density 0.035%

    No Known Activations