© 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. 115309
    Prev
    Next
    INDEX
    Explanations

    my little girl, our beloved baby, precious ones

    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
     aver
    -0.11
    omens
    -0.11
     facet
    -0.10
    andr
    -0.10
    nat
    -0.10
     yourselves
    -0.10
     :\
    -0.09
     frat
    -0.09
     Adventures
    -0.09
     Shrine
    -0.09
    POSITIVE LOGITS
     darling
    0.20
     beloved
    0.18
     dear
    0.16
     little
    0.13
     precious
    0.13
     Darling
    0.12
    little
    0.12
     dearly
    0.11
     amore
    0.11
     sweet
    0.11
    Activations Density 0.065%

    No Known Activations