© 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. 16689
    Prev
    Next
    INDEX
    Explanations

    can't resist

    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
     Bast
    -0.09
     whit
    -0.09
     unpleasant
    -0.08
    udios
    -0.08
     gerne
    -0.08
     Lange
    -0.08
     Hull
    -0.08
     Morrison
    -0.08
    pleasant
    -0.08
     cons
    -0.08
    POSITIVE LOGITS
     temptation
    0.26
     irresistible
    0.22
     tempting
    0.22
     irresist
    0.21
     tempt
    0.19
     resist
    0.19
     tempted
    0.19
    tempt
    0.19
     impulse
    0.18
     impulses
    0.17
    Activations Density 0.052%

    No Known Activations