© 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. 30741
    Prev
    Next
    INDEX
    Explanations

    safe environment

    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
     ineligible
    -0.11
     Bang
    -0.10
     Bare
    -0.10
     flashy
    -0.10
     ench
    -0.10
     bang
    -0.10
     reminis
    -0.10
     quot
    -0.10
     primitive
    -0.09
     Inline
    -0.09
    POSITIVE LOGITS
     safe
    0.40
     safely
    0.34
     Safe
    0.33
    safe
    0.32
    Safe
    0.31
    -safe
    0.30
     supportive
    0.27
     SAFE
    0.26
     saf
    0.24
     confidential
    0.23
    Activations Density 0.079%

    No Known Activations