© 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. 27492
    Prev
    Next
    INDEX
    Explanations

    safe environment or haven

    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
     Roch
    -0.10
     brisk
    -0.10
    orda
    -0.09
     FPS
    -0.09
     Rescue
    -0.09
     Rom
    -0.09
     mercy
    -0.09
    wise
    -0.09
     spontaneous
    -0.08
     Dor
    -0.08
    POSITIVE LOGITS
     environment
    0.22
     envi
    0.17
     space
    0.16
    çݯ
    0.14
     Environment
    0.14
     environments
    0.14
     forum
    0.13
    Environment
    0.13
     venue
    0.13
     outlet
    0.13
    Activations Density 0.014%

    No Known Activations