© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91958
    Prev
    Next
    INDEX
    Explanations

    Madison

    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
    stones
    -0.10
    man
    -0.09
    ustr
    -0.09
    sville
    -0.09
    orro
    -0.09
    ness
    -0.09
    åĪ¶
    -0.08
    er
    -0.08
    ting
    -0.08
    eding
    -0.08
    POSITIVE LOGITS
    ally
    0.14
    ivy
    0.13
    nel
    0.12
    nelle
    0.11
    ality
    0.10
    æģ¯
    0.10
     Dear
    0.09
    nette
    0.09
    volt
    0.09
    ëĭĪëĭ¤
    0.09
    Activations Density 0.009%

    No Known Activations