© 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. 47357
    Prev
    Next
    INDEX
    Explanations

    excuse or justification

    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
    prep
    -0.10
     Suff
    -0.10
    unar
    -0.09
     pled
    -0.09
     Amen
    -0.09
     rot
    -0.09
    ablo
    -0.09
     Daniels
    -0.09
    bers
    -0.08
    uzzi
    -0.08
    POSITIVE LOGITS
     excuse
    0.54
     excuses
    0.44
     pretext
    0.43
     justification
    0.36
     justify
    0.34
     justified
    0.28
     rationale
    0.22
     reason
    0.21
    justify
    0.20
     opportunity
    0.20
    Activations Density 0.150%

    No Known Activations