© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48277
    Prev
    Next
    INDEX
    Explanations

    great-grand relations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Minority
    -0.09
     adjoining
    -0.09
     simultaneous
    -0.09
     Lover
    -0.09
     cord
    -0.09
    lan
    -0.08
     minorities
    -0.08
    /com
    -0.08
     sess
    -0.08
    sek
    -0.08
    POSITIVE LOGITS
     descend
    0.22
     grandchildren
    0.22
     descendants
    0.21
     ancestor
    0.21
     ancestors
    0.21
     grandfather
    0.20
     descended
    0.20
     descendant
    0.20
     grandparents
    0.20
     desc
    0.19
    Activations Density 0.079%

    No Known Activations