© 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. 90558
    Prev
    Next
    INDEX
    Explanations

    admitting sins/confession

    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
     respectful
    -0.12
     hosp
    -0.12
     ster
    -0.11
     abrupt
    -0.11
     logistical
    -0.11
     respect
    -0.10
     courteous
    -0.10
     irritated
    -0.10
    ernes
    -0.10
     Cox
    -0.10
    POSITIVE LOGITS
     confess
    0.49
     confession
    0.48
     confessed
    0.43
     guilt
    0.34
     sins
    0.33
     repent
    0.29
     guilty
    0.29
     sin
    0.29
     remorse
    0.27
     admitting
    0.26
    Activations Density 0.156%

    No Known Activations