© 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. 4799
    Prev
    Next
    INDEX
    Explanations

    welcoming guests and hospitality

    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
     blackmail
    -0.09
     locker
    -0.09
     Carb
    -0.09
     penetration
    -0.08
     penetr
    -0.08
     carb
    -0.08
    ederland
    -0.08
     dod
    -0.08
     destructive
    -0.08
     alignment
    -0.07
    POSITIVE LOGITS
     hospitality
    0.45
     hosp
    0.39
     welcoming
    0.39
     guests
    0.36
     Hospitality
    0.35
     guest
    0.33
     Guests
    0.31
     hosting
    0.31
     welcome
    0.31
     host
    0.31
    Activations Density 0.144%

    No Known Activations