© 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. 90659
    Prev
    Next
    INDEX
    Explanations

    clad, laden, describing coverings or fillings

    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
    chin
    -0.12
    yer
    -0.11
    erer
    -0.11
    grund
    -0.10
    idak
    -0.10
    rott
    -0.10
    fur
    -0.10
    blick
    -0.10
     fray
    -0.10
    requ
    -0.10
    POSITIVE LOGITS
    ings
    0.13
    INGS
    0.08
    rib
    0.08
     desn
    0.07
     tighter
    0.07
    Craft
    0.07
    ines
    0.07
     slippery
    0.07
    ments
    0.07
     peril
    0.07
    Activations Density 0.002%

    No Known Activations