© 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. 5133
    Prev
    Next
    INDEX
    Explanations

    entryway, hall, or porch

    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
     Vog
    -0.10
     misog
    -0.10
     signaled
    -0.09
     drifting
    -0.09
    strstr
    -0.09
     Merr
    -0.09
     workforce
    -0.09
     misogyn
    -0.09
     Cheney
    -0.09
    asar
    -0.08
    POSITIVE LOGITS
     entrance
    0.14
     leading
    0.13
     Entrance
    0.12
    leading
    0.11
     entry
    0.10
     doorway
    0.10
     linking
    0.10
     vestib
    0.10
     hallway
    0.10
    between
    0.10
    Activations Density 0.046%

    No Known Activations