© 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. 4754
    Prev
    Next
    INDEX
    Explanations

    murdered people and related crimes

    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
     naughty
    -0.13
     chast
    -0.11
     punt
    -0.11
     Keynes
    -0.11
     demi
    -0.10
     cuck
    -0.10
     contingency
    -0.10
     pun
    -0.10
     rej
    -0.10
     crap
    -0.10
    POSITIVE LOGITS
     trag
    0.28
     murdered
    0.26
     tragic
    0.25
     murder
    0.24
     homicide
    0.23
     tragedy
    0.22
     murders
    0.22
     Murder
    0.21
     tragedies
    0.21
     killers
    0.21
    Activations Density 1.615%

    No Known Activations