© 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. 112381
    Prev
    Next
    INDEX
    Explanations

    strip

    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
    iste
    -0.09
     Male
    -0.09
     Fetish
    -0.09
     focal
    -0.08
    Male
    -0.08
     Auth
    -0.08
     reve
    -0.08
     Managed
    -0.08
    uro
    -0.08
     stubborn
    -0.08
    POSITIVE LOGITS
     someday
    0.12
     stripped
    0.11
     strip
    0.11
     stripping
    0.10
    ocos
    0.10
     dismantle
    0.10
     Webster
    0.10
    strip
    0.10
     hos
    0.10
     chop
    0.10
    Activations Density 0.035%

    No Known Activations