© 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. 31764
    Prev
    Next
    INDEX
    Explanations

    wetness and moisture

    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
     Dixon
    -0.13
     moist
    -0.10
     aque
    -0.10
     Bucc
    -0.09
    èĪ
    -0.09
     hydrated
    -0.08
     Sadd
    -0.08
     urinary
    -0.08
     dew
    -0.08
    EmailAddress
    -0.08
    POSITIVE LOGITS
     clothes
    0.15
     clothing
    0.13
     hair
    0.12
     Clothes
    0.12
    hair
    0.11
    kel
    0.11
     drafts
    0.10
    ened
    0.10
    dra
    0.10
     footprint
    0.10
    Activations Density 0.018%

    No Known Activations