© 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. 3457
    Prev
    Next
    INDEX
    Explanations

    seeking intentions and goals

    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
     familiar
    -0.10
     tactile
    -0.10
     physically
    -0.09
     familiarity
    -0.09
     Pey
    -0.09
     synthes
    -0.08
    -pe
    -0.08
     manual
    -0.08
     PRIV
    -0.08
     SCT
    -0.08
    POSITIVE LOGITS
     intentions
    0.24
     Intent
    0.19
    Intent
    0.19
    intent
    0.18
     intent
    0.18
     seeking
    0.18
     intention
    0.17
     goals
    0.16
    seek
    0.16
     casually
    0.15
    Activations Density 0.053%

    No Known Activations