© 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. 7880
    Prev
    Next
    INDEX
    Explanations

    provoked/dirty/bloody text fragments

    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
    bai
    -0.11
     Ara
    -0.10
    mant
    -0.10
    reh
    -0.09
     Dana
    -0.09
     overloaded
    -0.09
    ices
    -0.09
     Warp
    -0.09
    DEM
    -0.09
    elden
    -0.09
    POSITIVE LOGITS
     dirty
    0.09
     angered
    0.09
     provoc
    0.09
    els
    0.09
    prov
    0.08
     Dirty
    0.08
     bloody
    0.08
     provoked
    0.08
     provocative
    0.08
     reli
    0.08
    Activations Density 0.159%

    No Known Activations