© 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. 15441
    Prev
    Next
    INDEX
    Explanations

    free speech

    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
     divorce
    -0.12
     confess
    -0.10
     divor
    -0.10
     loft
    -0.10
     shrink
    -0.10
     incest
    -0.10
     noct
    -0.10
     celib
    -0.10
     inherit
    -0.10
     confidentiality
    -0.10
    POSITIVE LOGITS
     breastfeeding
    0.17
     beach
    0.16
     beaches
    0.16
     breast
    0.15
     breasts
    0.14
     public
    0.14
     Breast
    0.14
     nipple
    0.13
     shirt
    0.13
     wearer
    0.13
    Activations Density 0.081%

    No Known Activations