© 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. 26412
    Prev
    Next
    INDEX
    Explanations

    violence and crime targeting groups

    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
     Holding
    -0.12
     Mell
    -0.11
     outr
    -0.11
     Economist
    -0.11
     Pars
    -0.11
    WR
    -0.11
     pager
    -0.11
     Pentagon
    -0.10
     DEC
    -0.10
    Rank
    -0.10
    POSITIVE LOGITS
     predators
    0.08
    acent
    0.07
     opposed
    0.07
    icient
    0.07
     Ballard
    0.07
     Bren
    0.07
     stalk
    0.07
    erg
    0.07
     accidents
    0.07
     jealous
    0.07
    Activations Density 0.001%

    No Known Activations