© 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. 33996
    Prev
    Next
    INDEX
    Explanations

    drawn to something

    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
     Palmer
    -0.10
    igin
    -0.10
    394
    -0.10
    dad
    -0.10
    YP
    -0.09
     Hampshire
    -0.09
     reap
    -0.09
     hei
    -0.09
    APP
    -0.09
     whit
    -0.09
    POSITIVE LOGITS
     attracted
    0.20
     attraction
    0.19
     grav
    0.18
     towards
    0.17
     toward
    0.16
     drawn
    0.16
     attractions
    0.15
     attract
    0.15
     irresist
    0.14
    attr
    0.13
    Activations Density 0.010%

    No Known Activations