© 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. 28333
    Prev
    Next
    INDEX
    Explanations

    hotel descriptions

    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
    olen
    -0.12
    achine
    -0.11
    jong
    -0.11
    Headers
    -0.11
    bare
    -0.11
     natives
    -0.11
     stall
    -0.10
    tees
    -0.10
    ilit
    -0.10
    irs
    -0.10
    POSITIVE LOGITS
     hotel
    0.21
     hotels
    0.20
     accommodations
    0.19
     Hotel
    0.19
     accommodation
    0.17
     Hotels
    0.16
     lodging
    0.16
     hospitality
    0.15
    Hotel
    0.15
     luxury
    0.15
    Activations Density 0.213%

    No Known Activations