© 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. 112592
    Prev
    Next
    INDEX
    Explanations

    girl princess fairy tales

    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
     cooler
    -0.12
     condom
    -0.11
     rept
    -0.11
     Ej
    -0.11
     coolest
    -0.10
     Sphinx
    -0.10
     Epic
    -0.10
     towel
    -0.10
     Scor
    -0.10
     hus
    -0.10
    POSITIVE LOGITS
     cute
    0.22
     dolls
    0.22
     doll
    0.22
     pink
    0.21
     Barbie
    0.21
     Doll
    0.20
     gigg
    0.20
     gir
    0.20
     innocence
    0.20
     Cute
    0.19
    Activations Density 0.124%

    No Known Activations