© 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. 31316
    Prev
    Next
    INDEX
    Explanations

    excuse or disguise

    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
     reversing
    -0.13
    åıį
    -0.12
     reversal
    -0.12
     tables
    -0.11
     reversed
    -0.10
     quant
    -0.10
     revers
    -0.10
     recip
    -0.10
    à¸ľ
    -0.10
    463
    -0.10
    POSITIVE LOGITS
     pretext
    0.28
     disguise
    0.25
     excuse
    0.24
     fronts
    0.23
     guise
    0.22
     thinly
    0.21
     secretly
    0.20
     cover
    0.19
     excuses
    0.19
     facade
    0.18
    Activations Density 0.148%

    No Known Activations