© 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. 32098
    Prev
    Next
    INDEX
    Explanations

    people gathered

    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
     lone
    -0.13
     alone
    -0.13
    åı¸
    -0.12
     Alone
    -0.12
     deflect
    -0.11
     sole
    -0.11
     solo
    -0.11
     duo
    -0.11
     Mach
    -0.11
    alone
    -0.10
    POSITIVE LOGITS
     gathered
    0.23
     collectively
    0.22
     clustered
    0.20
     assembled
    0.19
     congreg
    0.18
     surrounding
    0.17
     gather
    0.17
     converge
    0.16
     Gather
    0.15
     applaud
    0.15
    Activations Density 0.223%

    No Known Activations