© 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. 49010
    Prev
    Next
    INDEX
    Explanations

    conspiracy theories and evil intentions

    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
     arguably
    -0.12
     frankly
    -0.10
     slap
    -0.10
     Prev
    -0.10
    bd
    -0.10
     blat
    -0.10
     hitch
    -0.10
    adier
    -0.10
     frank
    -0.10
     unofficial
    -0.10
    POSITIVE LOGITS
     conspir
    0.25
     conspiracy
    0.23
     evil
    0.22
     nef
    0.18
     evils
    0.18
     Evil
    0.18
     Conspiracy
    0.17
     sinister
    0.17
    evil
    0.17
     somehow
    0.14
    Activations Density 0.203%

    No Known Activations