© 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. 3570
    Prev
    Next
    INDEX
    Explanations

    need for validation and approval

    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
    aub
    -0.12
     Ged
    -0.11
     embarrassed
    -0.10
    ahas
    -0.10
     departing
    -0.10
    ensions
    -0.10
     vive
    -0.10
     advant
    -0.09
     delaying
    -0.09
     mounting
    -0.09
    POSITIVE LOGITS
     validation
    0.25
     Validation
    0.22
     craving
    0.21
     crave
    0.21
    /validation
    0.20
     affirmation
    0.20
    validation
    0.19
     needy
    0.19
     desperately
    0.19
     validate
    0.18
    Activations Density 0.044%

    No Known Activations