© 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. 31702
    Prev
    Next
    INDEX
    Explanations

    lymphocyte and related cell types

    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
     misplaced
    -0.10
    asp
    -0.10
    /met
    -0.09
    /co
    -0.09
    sun
    -0.09
    дал
    -0.09
    zo
    -0.09
    aldi
    -0.09
     Op
    -0.09
    -hidden
    -0.09
    POSITIVE LOGITS
     shaped
    0.13
    -shaped
    0.10
     Ranch
    0.10
     profound
    0.09
    finity
    0.09
     abre
    0.09
     pronounced
    0.09
     curve
    0.09
     fertil
    0.09
    Curve
    0.08
    Activations Density 0.322%

    No Known Activations