© 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. 89515
    Prev
    Next
    INDEX
    Explanations

    sexual or socially relevant contexts

    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
     Äijược
    -0.12
     ener
    -0.11
     paras
    -0.11
    IFO
    -0.11
     effortlessly
    -0.10
    aren
    -0.10
    /print
    -0.10
    haven
    -0.10
    pes
    -0.10
     anonymously
    -0.09
    POSITIVE LOGITS
     explicit
    0.11
     nudity
    0.10
     suggestive
    0.10
     provocative
    0.10
    -focus
    0.09
     explic
    0.09
     pand
    0.08
    fulness
    0.08
    911
    0.08
     nude
    0.08
    Activations Density 0.003%

    No Known Activations