© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    harm or safety

    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
     Saving
    -0.12
     saving
    -0.10
    ondo
    -0.10
     Intercept
    -0.10
     distraction
    -0.10
    /Form
    -0.10
    286
    -0.09
    eros
    -0.09
     plac
    -0.09
     saves
    -0.09
    POSITIVE LOGITS
     physically
    0.18
     physical
    0.13
     Physical
    0.11
    physical
    0.11
     PHYS
    0.10
     harm
    0.10
     fÃŃs
    0.10
     inher
    0.10
    phys
    0.10
     Phys
    0.10
    Activations Density 0.013%

    No Known Activations