© 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. 5946
    Prev
    Next
    INDEX
    Explanations

    both respectively former

    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
    ailer
    -0.09
    InOut
    -0.09
    urn
    -0.09
    rous
    -0.09
    ails
    -0.09
    arters
    -0.09
    AIL
    -0.08
    iolet
    -0.08
     dow
    -0.08
    Andre
    -0.08
    POSITIVE LOGITS
     latter
    0.19
     respectively
    0.18
     former
    0.18
    former
    0.13
    Former
    0.12
    both
    0.12
     resp
    0.10
     BOTH
    0.10
    Both
    0.10
     Former
    0.10
    Activations Density 1.995%

    No Known Activations