© 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. 89908
    Prev
    Next
    INDEX
    Explanations

    oral sex acts and things that are bad

    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
    istring
    -0.10
    enschaft
    -0.08
    uhe
    -0.07
     swath
    -0.07
     abducted
    -0.07
     signings
    -0.07
    _reading
    -0.07
    HIP
    -0.07
     jump
    -0.07
     rolling
    -0.07
    POSITIVE LOGITS
    pipes
    0.13
    indre
    0.11
     dick
    0.11
     toes
    0.11
    stakes
    0.11
     tits
    0.11
    -off
    0.10
     brains
    0.10
     Farr
    0.09
    modo
    0.09
    Activations Density 0.003%

    No Known Activations