© 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. 116462
    Prev
    Next
    INDEX
    Explanations

    safe and

    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
     Aware
    -0.09
     partially
    -0.09
     unknow
    -0.08
     lucky
    -0.08
     Lucky
    -0.08
    alach
    -0.08
     improperly
    -0.08
     inconsist
    -0.08
     compens
    -0.08
    ucha
    -0.08
    POSITIVE LOGITS
     harmless
    0.46
     safe
    0.40
     safely
    0.34
    -safe
    0.34
     Safe
    0.33
     safer
    0.32
    safe
    0.32
    Safe
    0.31
     safest
    0.30
     SAFE
    0.30
    Activations Density 1.199%

    No Known Activations