© 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. 111569
    Prev
    Next
    INDEX
    Explanations

    possessive family relationships

    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
     sufferers
    -0.08
     ones
    -0.08
     Lam
    -0.08
     needless
    -0.08
     dint
    -0.07
     seekers
    -0.07
     youngsters
    -0.07
     ladies
    -0.07
     guys
    -0.07
     youths
    -0.07
    POSITIVE LOGITS
     beloved
    0.14
     charismatic
    0.13
     dear
    0.13
     globally
    0.12
     Clover
    0.12
     always
    0.12
     suddenly
    0.12
     atheist
    0.12
     articulate
    0.12
     clo
    0.12
    Activations Density 0.049%

    No Known Activations