© 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. 16434
    Prev
    Next
    INDEX
    Explanations

    family relationships and friends

    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
     Mobility
    -0.10
     mobility
    -0.10
    emas
    -0.09
    otos
    -0.09
    ymb
    -0.09
    avo
    -0.09
    igon
    -0.09
    ?p
    -0.09
     recru
    -0.09
     masse
    -0.09
    POSITIVE LOGITS
     divorced
    0.10
     Prem
    0.10
     friends
    0.10
     Canc
    0.09
     Owners
    0.09
     whose
    0.09
     reconnect
    0.09
    whose
    0.09
    ä»ĭ
    0.09
    Friends
    0.09
    Activations Density 0.225%

    No Known Activations