© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46056
    Prev
    Next
    INDEX
    Explanations

    do not

    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
    Negative Logits
     reluctance
    -0.15
    ingen
    -0.13
     postpon
    -0.13
     unwilling
    -0.12
     restraint
    -0.12
     refusal
    -0.11
     trunc
    -0.11
     hesitant
    -0.11
     refrain
    -0.11
     restrained
    -0.11
    POSITIVE LOGITS
     succ
    0.14
     tempted
    0.12
     jeopard
    0.12
     indul
    0.12
     stray
    0.10
     gratuit
    0.10
     foolish
    0.10
     accidentally
    0.10
     tempting
    0.10
     ever
    0.09
    Activations Density 0.043%

    No Known Activations