© 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. 28852
    Prev
    Next
    INDEX
    Explanations

    illegal or immoral acts

    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
     IDEA
    -0.09
     censorship
    -0.09
     etiquette
    -0.09
    enu
    -0.09
    _waiting
    -0.08
    ype
    -0.08
     collision
    -0.08
     triggered
    -0.07
     synth
    -0.07
     miscar
    -0.07
    POSITIVE LOGITS
     indiscrim
    0.17
     Rum
    0.13
     habitual
    0.13
     notorious
    0.12
    Prostit
    0.12
     commits
    0.12
     Pref
    0.12
     proficient
    0.12
     rampant
    0.12
     Prostit
    0.12
    Activations Density 0.027%

    No Known Activations