© 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. 29729
    Prev
    Next
    INDEX
    Explanations

    Naked Security, Man, body, eye, girls

    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
    iken
    -0.08
     consenting
    -0.07
     invol
    -0.07
    /el
    -0.07
     dissert
    -0.07
    pai
    -0.07
     bark
    -0.07
     concessions
    -0.07
     SHA
    -0.07
     Bark
    -0.07
    POSITIVE LOGITS
    ness
    0.15
     Hamm
    0.13
    ãĤĮ
    0.11
    lashes
    0.10
     truth
    0.10
    dar
    0.10
    foot
    0.10
     Radi
    0.10
     minim
    0.10
    unft
    0.10
    Activations Density 0.014%

    No Known Activations