© 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. 90731
    Prev
    Next
    INDEX
    Explanations

    who shot someone

    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
    umba
    -0.10
    omm
    -0.10
     alike
    -0.09
     Redemption
    -0.09
    thy
    -0.09
     contingency
    -0.09
     Jail
    -0.09
    669
    -0.09
    Ñĥм
    -0.09
    headline
    -0.09
    POSITIVE LOGITS
     whoever
    0.42
     Whoever
    0.40
     culprit
    0.32
     perpetrator
    0.28
     Who
    0.26
    Who
    0.25
     perpetrators
    0.25
     who
    0.23
     suspects
    0.22
    who
    0.20
    Activations Density 0.547%

    No Known Activations