© 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. 115631
    Prev
    Next
    INDEX
    Explanations

    stripping off layers or covering

    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
     orchestra
    -0.11
     ide
    -0.10
     Singer
    -0.10
     Actors
    -0.10
     singers
    -0.09
     sui
    -0.09
     sung
    -0.09
     opera
    -0.09
     actors
    -0.09
     prostitution
    -0.09
    POSITIVE LOGITS
     stripping
    0.15
     stripped
    0.14
    stri
    0.12
     strip
    0.10
     bare
    0.10
     deco
    0.10
     revelations
    0.10
     peeled
    0.10
    strip
    0.10
     stri
    0.09
    Activations Density 0.004%

    No Known Activations