© 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. 89872
    Prev
    Next
    INDEX
    Explanations

    underwear

    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
    rend
    -0.09
     hc
    -0.08
     Herm
    -0.08
     Abr
    -0.08
    gest
    -0.08
     bab
    -0.08
     rog
    -0.08
    IDEO
    -0.07
     apprentices
    -0.07
    fel
    -0.07
    POSITIVE LOGITS
     underwear
    0.28
     bare
    0.20
     paj
    0.16
     unders
    0.15
     panties
    0.15
     socks
    0.15
     skeleton
    0.14
     lingerie
    0.14
     stripped
    0.14
    -shirt
    0.13
    Activations Density 0.084%

    No Known Activations