© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 25240
    Prev
    Next
    INDEX
    Explanations

    supplies or items stocked

    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
    ulo
    -0.09
     Witt
    -0.09
     funnel
    -0.09
     ballo
    -0.09
     Unblock
    -0.09
     pseud
    -0.08
    usk
    -0.08
    oku
    -0.08
     Ober
    -0.08
    åĭ
    -0.08
    POSITIVE LOGITS
     stocked
    0.40
     cupboard
    0.38
     pantry
    0.38
     stash
    0.36
     inventory
    0.32
     supplies
    0.32
     drawer
    0.32
     cabinet
    0.30
     stock
    0.30
     cabinets
    0.30
    Activations Density 0.493%

    No Known Activations