© 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. 49770
    Prev
    Next
    INDEX
    Explanations

    beauty and makeup

    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
     ping
    -0.11
     unde
    -0.10
     Ping
    -0.09
     raft
    -0.08
     Inch
    -0.08
     Norton
    -0.08
    ping
    -0.08
     perplex
    -0.08
     wol
    -0.08
    illow
    -0.08
    POSITIVE LOGITS
     cosmetics
    0.12
     chocolates
    0.11
     Makeup
    0.11
     hairstyles
    0.10
     Hairst
    0.10
     Sah
    0.10
     makeup
    0.09
     Maiden
    0.09
     GK
    0.09
     hairst
    0.09
    Activations Density 0.002%

    No Known Activations