© 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. 26908
    Prev
    Next
    INDEX
    Explanations

    sexual content and scientific terms

    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
     iota
    -0.11
     cuffs
    -0.11
    deaux
    -0.10
    ieg
    -0.10
     bureaucr
    -0.10
     nack
    -0.10
    arem
    -0.10
     licked
    -0.10
     carte
    -0.10
    plash
    -0.10
    POSITIVE LOGITS
    ied
    0.09
    ed
    0.09
    iber
    0.08
    /high
    0.08
     sham
    0.08
     black
    0.08
     Kay
    0.08
    pj
    0.08
     Published
    0.08
     dest
    0.07
    Activations Density 0.003%

    No Known Activations