© 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. 18089
    Prev
    Next
    INDEX
    Explanations

    cruelty, sad, pleasure

    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
     reconc
    -0.10
     reconciliation
    -0.10
     NRF
    -0.09
    quat
    -0.09
     fertility
    -0.09
     Phoenix
    -0.09
     Chore
    -0.09
    twig
    -0.09
     vul
    -0.09
     fart
    -0.08
    POSITIVE LOGITS
     cruelty
    0.15
     Cru
    0.14
     pleasure
    0.13
     Sad
    0.13
     vamp
    0.13
    Sad
    0.13
     cru
    0.12
     sad
    0.12
     narciss
    0.12
    sad
    0.12
    Activations Density 0.019%

    No Known Activations