© 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. 112703
    Prev
    Next
    INDEX
    Explanations

    smell

    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
     hands
    -0.10
    raj
    -0.10
     attracting
    -0.10
    ÑĢан
    -0.10
    /Internal
    -0.10
    agit
    -0.10
     adorable
    -0.10
     fins
    -0.10
     apar
    -0.09
     Stephens
    -0.09
    POSITIVE LOGITS
     stale
    0.16
     dusty
    0.16
     salty
    0.14
     stagnant
    0.14
     damp
    0.14
     sterile
    0.13
     dirt
    0.13
     dry
    0.12
     salt
    0.12
     dust
    0.12
    Activations Density 0.013%

    No Known Activations