© 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. 117033
    Prev
    Next
    INDEX
    Explanations

    disgusting, gross, repulsed

    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
     fractured
    -0.12
     irresponsible
    -0.12
     mischief
    -0.12
     irres
    -0.10
     frustr
    -0.10
     sass
    -0.10
    shal
    -0.10
     lumber
    -0.09
    IDD
    -0.09
     stripped
    -0.09
    POSITIVE LOGITS
     disgust
    0.49
     disgusted
    0.46
     disgusting
    0.41
     nause
    0.35
     vom
    0.28
     nausea
    0.27
     gag
    0.27
     gross
    0.27
     Gross
    0.26
     repell
    0.26
    Activations Density 0.093%

    No Known Activations