© 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. 17995
    Prev
    Next
    INDEX
    Explanations

    positive actions and 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
     supposedly
    -0.12
     Opinion
    -0.12
     opinion
    -0.12
     theoret
    -0.11
     Platt
    -0.11
     Op
    -0.11
     Mixing
    -0.11
    ç¨į
    -0.11
     seemingly
    -0.11
     slightly
    -0.10
    POSITIVE LOGITS
     beneficial
    0.27
     positive
    0.26
     constructive
    0.25
     conducive
    0.24
     healthy
    0.24
     healthier
    0.24
     Positive
    0.23
     Healthy
    0.20
     positively
    0.20
     supportive
    0.20
    Activations Density 0.741%

    No Known Activations