© 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. 31565
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and applications

    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
     hormones
    -0.11
     cannabinoids
    -0.11
     hormonal
    -0.11
     herbs
    -0.10
     steroids
    -0.10
     pollutants
    -0.09
     THC
    -0.09
     hormone
    -0.09
    /hash
    -0.09
    wor
    -0.09
    POSITIVE LOGITS
    CAS
    0.18
     CAS
    0.17
     Sigma
    0.13
     Coleman
    0.13
     industrial
    0.12
     Wikipedia
    0.12
     FEMA
    0.12
     wikipedia
    0.12
     wik
    0.12
     applications
    0.11
    Activations Density 1.891%

    No Known Activations