© 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. 6726
    Prev
    Next
    INDEX
    Explanations

    entering or piercing

    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
    amd
    -0.12
    rok
    -0.12
     leaning
    -0.11
     appreh
    -0.10
     leans
    -0.10
     tal
    -0.10
     supplemental
    -0.10
    rais
    -0.09
     shorts
    -0.09
    -footer
    -0.09
    POSITIVE LOGITS
     penetr
    0.13
     penetrate
    0.13
     penetrating
    0.13
     invading
    0.11
     Tra
    0.11
     tra
    0.11
     pier
    0.10
     repeatedly
    0.10
     pulver
    0.10
     piercing
    0.10
    Activations Density 0.007%

    No Known Activations