© 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. 27914
    Prev
    Next
    INDEX
    Explanations

    appropriate delivery, transcription, toilet, MIC, source

    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
     ones
    -0.12
    itas
    -0.09
    aban
    -0.09
     ladies
    -0.09
    kins
    -0.09
     conseg
    -0.08
    ozo
    -0.08
    iant
    -0.08
     sections
    -0.08
     sisters
    -0.08
    POSITIVE LOGITS
     specialised
    0.23
     specialized
    0.23
     specially
    0.18
     dedicated
    0.17
     special
    0.16
    ä¸ĵ
    0.14
     specialist
    0.14
     especial
    0.13
    special
    0.13
     appropriate
    0.12
    Activations Density 2.016%

    No Known Activations