© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117366
    Prev
    Next
    INDEX
    Explanations

    mushroom or fungus

    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
    Negative Logits
     JAXB
    -0.11
     dove
    -0.11
     SVN
    -0.10
     icy
    -0.10
     XML
    -0.10
     Petty
    -0.09
     Tire
    -0.09
     runway
    -0.09
     Engines
    -0.09
     ice
    -0.09
    POSITIVE LOGITS
     mushroom
    0.55
     mushrooms
    0.50
     Mushroom
    0.49
     fungus
    0.43
     fungi
    0.43
     Mush
    0.42
     fungal
    0.42
    fung
    0.37
     fung
    0.32
     mush
    0.20
    Activations Density 0.619%

    No Known Activations