© 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. 90381
    Prev
    Next
    INDEX
    Explanations

    phosphorus compounds

    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
     stemmed
    -0.08
     Heavenly
    -0.08
    Internal
    -0.08
     weakening
    -0.08
     Internal
    -0.08
     Hag
    -0.07
     rec
    -0.07
    ÙĪÙĦ
    -0.07
    esi
    -0.07
    mai
    -0.07
    POSITIVE LOGITS
    belt
    0.12
    edBy
    0.11
    CTRL
    0.11
    eo
    0.10
    pedia
    0.10
     ============================================================================↵
    0.10
     odp
    0.10
    ory
    0.10
    verse
    0.10
    edo
    0.10
    Activations Density 0.027%

    No Known Activations