© 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. 91832
    Prev
    Next
    INDEX
    Explanations

    velvet

    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
    aceous
    -0.10
    alette
    -0.09
     Lands
    -0.09
    als
    -0.09
    mits
    -0.09
    holds
    -0.09
    eree
    -0.09
    acco
    -0.09
    alist
    -0.08
    holders
    -0.08
    POSITIVE LOGITS
    ting
    0.13
    ted
    0.12
     Underground
    0.12
    -corner
    0.11
    kommen
    0.11
    tri
    0.10
     latter
    0.10
    cro
    0.10
     propri
    0.10
    ripe
    0.09
    Activations Density 0.009%

    No Known Activations