© 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. 27102
    Prev
    Next
    INDEX
    Explanations

    implicit and explicit concepts

    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
    s
    -0.12
    sit
    -0.10
     Prev
    -0.08
     prevalent
    -0.08
     seating
    -0.08
     fifteen
    -0.08
     Muhammad
    -0.08
     Mohammad
    -0.08
     Mohammed
    -0.08
    rox
    -0.08
    POSITIVE LOGITS
    ely
    0.18
    /exp
    0.17
    ELY
    0.13
    oes
    0.12
     mentioning
    0.11
     mention
    0.11
     explicitly
    0.11
     Explicit
    0.11
    Explicit
    0.11
     forbid
    0.10
    Activations Density 0.047%

    No Known Activations