© 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. 17138
    Prev
    Next
    INDEX
    Explanations

    strangled, drowned, asphyxia

    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
     Canonical
    -0.09
     Wick
    -0.09
     cracking
    -0.09
     Decomp
    -0.08
     Pas
    -0.08
     cracked
    -0.08
     maiden
    -0.08
     Nik
    -0.08
     Explos
    -0.08
     Maiden
    -0.08
    POSITIVE LOGITS
     choking
    0.20
     choke
    0.19
     choked
    0.16
     suff
    0.16
     strang
    0.15
     drowning
    0.14
     thrott
    0.13
    /star
    0.13
     drowned
    0.13
     stif
    0.12
    Activations Density 0.028%

    No Known Activations