© 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. 17784
    Prev
    Next
    INDEX
    Explanations

    cute or adorable descriptions

    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
     guru
    -0.10
     reputed
    -0.10
     luxurious
    -0.09
     rar
    -0.09
     resil
    -0.09
     Ment
    -0.09
     glory
    -0.09
     glorious
    -0.09
     incred
    -0.09
     elite
    -0.09
    POSITIVE LOGITS
     cute
    0.23
     adorable
    0.22
     Cute
    0.18
     cudd
    0.16
     chubby
    0.15
     fuzzy
    0.13
     innocent
    0.12
     charming
    0.12
     puppy
    0.12
     kitten
    0.12
    Activations Density 0.015%

    No Known Activations