© 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. 115567
    Prev
    Next
    INDEX
    Explanations

    at home or convenient locations

    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
     Verm
    -0.09
    Builders
    -0.09
     underwater
    -0.09
     scal
    -0.09
     sond
    -0.09
     onboard
    -0.08
     FuÃŁ
    -0.08
     Bru
    -0.08
     inline
    -0.08
     tamp
    -0.08
    POSITIVE LOGITS
     convenience
    0.13
     environment
    0.12
     surroundings
    0.12
     premises
    0.11
     comfort
    0.11
    /home
    0.11
     convenient
    0.10
    /workspace
    0.10
     Zig
    0.10
     Advent
    0.10
    Activations Density 0.046%

    No Known Activations