© 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. 113951
    Prev
    Next
    INDEX
    Explanations

    penetrating 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
     physic
    -0.09
     taste
    -0.08
     caught
    -0.08
     inclination
    -0.08
     away
    -0.08
     blinking
    -0.08
     kepada
    -0.08
     intellig
    -0.08
     challenged
    -0.08
     undone
    -0.08
    POSITIVE LOGITS
     penetr
    0.19
     penetration
    0.18
     penetrate
    0.17
     penetrated
    0.16
     penetrating
    0.14
     penet
    0.14
     piercing
    0.14
     deeply
    0.14
     holes
    0.13
     depths
    0.13
    Activations Density 0.077%

    No Known Activations