© 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. 115775
    Prev
    Next
    INDEX
    Explanations

    home and convenience services

    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
    Cel
    -0.12
     expo
    -0.11
     autorelease
    -0.11
    stown
    -0.11
    igham
    -0.10
    ıkl
    -0.10
    ullan
    -0.10
     mans
    -0.10
    bounce
    -0.10
    -directory
    -0.10
    POSITIVE LOGITS
     home
    0.18
     convenience
    0.16
    -home
    0.15
     Home
    0.15
     doorstep
    0.14
     Convenience
    0.14
    .home
    0.13
    home
    0.13
     intimate
    0.13
     privacy
    0.13
    Activations Density 0.050%

    No Known Activations