© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114623
    Prev
    Next
    INDEX
    Explanations

    updating contents or life/worst

    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
    lux
    -0.10
     techn
    -0.10
     impressed
    -0.10
     flattering
    -0.09
     Maison
    -0.09
     vanity
    -0.09
     likes
    -0.09
     elit
    -0.08
    DAL
    -0.08
    emple
    -0.08
    POSITIVE LOGITS
     paranoia
    0.16
     avoided
    0.14
     covert
    0.13
     avoidance
    0.13
     guilt
    0.13
     suspicions
    0.12
     paranoid
    0.12
     renewed
    0.12
     Secret
    0.12
     normal
    0.12
    Activations Density 0.061%

    No Known Activations