© 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. 115266
    Prev
    Next
    INDEX
    Explanations

    remote, secluded, or scenic places

    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
    andon
    -0.09
    dac
    -0.08
    ake
    -0.08
     Lonely
    -0.08
     Shoes
    -0.08
     monument
    -0.08
     <->
    -0.08
    aves
    -0.08
     Sek
    -0.08
     bib
    -0.08
    POSITIVE LOGITS
    ness
    0.16
     spot
    0.15
    /private
    0.15
     spots
    0.14
     alc
    0.13
     corners
    0.12
     corner
    0.12
     areas
    0.12
    spot
    0.11
    /Private
    0.11
    Activations Density 0.020%

    No Known Activations