© 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. 5661
    Prev
    Next
    INDEX
    Explanations

    preventing negative outcomes

    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
     everywhere
    -0.13
     Everywhere
    -0.10
     Sever
    -0.10
     observ
    -0.10
     flaw
    -0.10
     ancest
    -0.10
     challenge
    -0.10
     facts
    -0.10
     restrained
    -0.10
    be
    -0.09
    POSITIVE LOGITS
     surprises
    0.23
     misunderstand
    0.23
     unnecessary
    0.23
     pitfalls
    0.22
     situations
    0.20
     unwanted
    0.20
     potential
    0.19
     mistakes
    0.18
     costly
    0.18
     accidents
    0.17
    Activations Density 0.226%

    No Known Activations