© 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. 50547
    Prev
    Next
    INDEX
    Explanations

    misuse of tech platforms and harms

    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
    Mini
    -0.11
     cola
    -0.10
     cla
    -0.10
     Accident
    -0.10
     mini
    -0.10
    OAD
    -0.10
    ipop
    -0.10
     Sur
    -0.10
     incomes
    -0.10
     sitcom
    -0.10
    POSITIVE LOGITS
     tech
    0.13
     Lau
    0.12
     intermedi
    0.12
     abuse
    0.12
     misuse
    0.11
     platforms
    0.11
     abused
    0.11
     knowingly
    0.11
     Tech
    0.10
     harms
    0.10
    Activations Density 0.124%

    No Known Activations