© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    defamation judgment

    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
     servicing
    -0.10
     misunderstood
    -0.10
    -Re
    -0.09
     misunder
    -0.09
    eting
    -0.09
    ales
    -0.09
     consenting
    -0.09
    inel
    -0.09
     outs
    -0.09
    -dat
    -0.09
    POSITIVE LOGITS
    /dis
    0.09
     broadly
    0.09
     dignity
    0.09
    o
    0.08
    goo
    0.08
    lew
    0.08
     Lew
    0.08
     thorough
    0.08
    nth
    0.08
    ìĹ
    0.08
    Activations Density 0.002%

    No Known Activations