© 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. 27398
    Prev
    Next
    INDEX
    Explanations

    social media, news, science, ethics, isolation

    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
     sill
    -0.09
    oops
    -0.09
    ibi
    -0.09
    anim
    -0.08
    alian
    -0.08
    -body
    -0.08
     Massage
    -0.08
     HIM
    -0.08
     OPT
    -0.08
    æ±
    -0.08
    POSITIVE LOGITS
     isolated
    0.11
     isolation
    0.10
     socially
    0.10
    ocial
    0.10
    isol
    0.09
     distancing
    0.09
    nie
    0.09
    inery
    0.09
    iskey
    0.09
     isol
    0.09
    Activations Density 0.011%

    No Known Activations