© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    negative traits and actions

    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
     massac
    -0.13
     compassionate
    -0.12
     massacre
    -0.12
     sensible
    -0.11
     egal
    -0.11
     understandably
    -0.11
     altru
    -0.11
     parch
    -0.11
     saints
    -0.11
     heroic
    -0.11
    POSITIVE LOGITS
     manip
    0.18
     narciss
    0.15
     cunning
    0.14
     opportun
    0.14
     spite
    0.13
     dangerous
    0.13
     coward
    0.13
     manipulating
    0.12
     pathological
    0.12
     Manip
    0.12
    Activations Density 0.194%

    No Known Activations