© 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. 5953
    Prev
    Next
    INDEX
    Explanations

    formula or formulation

    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
     Lair
    -0.11
    allery
    -0.11
     depreci
    -0.11
     Blake
    -0.10
    opian
    -0.10
    brains
    -0.10
    ettel
    -0.10
    IME
    -0.10
     Lia
    -0.10
     immortal
    -0.10
    POSITIVE LOGITS
     formulation
    0.15
     formulated
    0.12
     Natur
    0.12
     confidently
    0.12
     Formula
    0.12
     trusted
    0.11
     Confidence
    0.11
     naturally
    0.11
     gentle
    0.11
     natural
    0.11
    Activations Density 0.171%

    No Known Activations