© 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. 89696
    Prev
    Next
    INDEX
    Explanations

    possessive + family relationship

    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
     intra
    -0.12
     skinny
    -0.12
     longitudinal
    -0.12
     redhead
    -0.12
     implode
    -0.11
     thin
    -0.11
     Weiter
    -0.10
     municipal
    -0.10
     chor
    -0.10
    eken
    -0.10
    POSITIVE LOGITS
     father
    0.18
     brother
    0.14
     fathers
    0.14
     sister
    0.13
     lover
    0.12
     grandfather
    0.12
     sisters
    0.12
     uncle
    0.11
    father
    0.11
     adopt
    0.11
    Activations Density 0.079%

    No Known Activations