© 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. 29811
    Prev
    Next
    INDEX
    Explanations

    sexual / explicit content

    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
     hereby
    -0.12
     together
    -0.10
    uppet
    -0.10
     taken
    -0.09
     nowhere
    -0.09
     Dove
    -0.09
     chosen
    -0.08
     woven
    -0.08
     wins
    -0.08
     hearts
    -0.08
    POSITIVE LOGITS
     mastur
    0.10
     homo
    0.09
     heter
    0.09
     deceased
    0.09
     homosexual
    0.09
     pissed
    0.09
     porno
    0.09
     masturbating
    0.09
     resembled
    0.09
     Fucked
    0.08
    Activations Density 0.095%

    No Known Activations