© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    words starting with "Wh"

    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
    eus
    -0.12
    Rio
    -0.12
    salt
    -0.11
    arie
    -0.11
    filesystem
    -0.11
    ]:↵↵↵
    -0.11
     Greenwood
    -0.11
    asca
    -0.10
    upal
    -0.10
     aden
    -0.10
    POSITIVE LOGITS
     whore
    0.11
    hores
    0.08
    -wh
    0.08
     prostitut
    0.08
     wh
    0.08
    ande
    0.07
     Wh
    0.07
     broth
    0.07
     shaved
    0.07
     hook
    0.07
    Activations Density 0.001%

    No Known Activations