© 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. 5769
    Prev
    Next
    INDEX
    Explanations

    door welcome inviting

    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
     camps
    -0.11
     Fin
    -0.11
    omo
    -0.10
     sleeper
    -0.10
     camp
    -0.09
     outputs
    -0.09
     interpolated
    -0.09
     padd
    -0.09
     spectral
    -0.08
    fin
    -0.08
    POSITIVE LOGITS
     doorstep
    0.27
     door
    0.27
     Door
    0.25
    Door
    0.23
     welcoming
    0.23
     invite
    0.22
     inviting
    0.22
    door
    0.21
     doorway
    0.21
     welcome
    0.21
    Activations Density 0.055%

    No Known Activations