© 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. 112016
    Prev
    Next
    INDEX
    Explanations

    law, justice, crime, legal, surgery, legislation

    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
    bras
    -0.10
    -inner
    -0.10
    обÑĭ
    -0.10
    们
    -0.09
    alia
    -0.09
    eno
    -0.09
     irrig
    -0.09
    sein
    -0.09
    -posts
    -0.09
    -ahead
    -0.09
    POSITIVE LOGITS
     penalties
    0.12
     Laf
    0.10
     prohibit
    0.09
    hone
    0.09
     fined
    0.09
    emat
    0.09
    igmat
    0.08
    ized
    0.08
     vill
    0.08
     Wel
    0.08
    Activations Density 0.001%

    No Known Activations