© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29378
    Prev
    Next
    INDEX
    Explanations

    close proximity

    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
     Stanton
    -0.10
     BF
    -0.10
     Glad
    -0.10
     exits
    -0.09
    gro
    -0.09
     ASCII
    -0.09
    STA
    -0.09
     ascii
    -0.09
     shouts
    -0.09
     bookmark
    -0.09
    POSITIVE LOGITS
     proximity
    0.24
     clos
    0.18
     close
    0.18
     Inches
    0.18
     inches
    0.17
     smell
    0.17
     Close
    0.17
     smelling
    0.16
     smelled
    0.16
     scent
    0.15
    Activations Density 0.047%

    No Known Activations