© 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. 91164
    Prev
    Next
    INDEX
    Explanations

    killing and murder

    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
     embarrass
    -0.13
     embarrassment
    -0.12
     vanity
    -0.12
     flirt
    -0.12
     embarrassing
    -0.12
     annoy
    -0.12
     chast
    -0.11
     Recovery
    -0.11
     Marriage
    -0.11
     marriage
    -0.11
    POSITIVE LOGITS
     killing
    0.45
     killings
    0.41
     kill
    0.38
     Killing
    0.38
     murder
    0.37
     murdering
    0.36
     kills
    0.36
     murders
    0.34
     slaughter
    0.33
     murderous
    0.31
    Activations Density 0.325%

    No Known Activations