© 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. 91222
    Prev
    Next
    INDEX
    Explanations

    safe

    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
     ticking
    -0.10
     Fountain
    -0.09
     fir
    -0.08
    arra
    -0.08
     wil
    -0.08
    sel
    -0.08
     invol
    -0.08
    substr
    -0.08
     Fle
    -0.08
     sharpen
    -0.08
    POSITIVE LOGITS
     safe
    0.30
    safe
    0.24
     Safe
    0.23
     safely
    0.22
     safer
    0.22
    Safe
    0.21
    SAFE
    0.21
     safest
    0.21
     coast
    0.20
    _safe
    0.19
    Activations Density 0.119%

    No Known Activations