© 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. 29915
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     legacy
    -0.09
    _legacy
    -0.08
    legacy
    -0.08
    Ø
    -0.08
    ãģķ
    -0.08
     fo
    -0.08
     Spencer
    -0.08
    lus
    -0.08
     Legacy
    -0.07
     conting
    -0.07
    POSITIVE LOGITS
    arent
    0.10
    (go
    0.10
    ELS
    0.10
    -tm
    0.10
     Bund
    0.10
    chy
    0.10
     Broad
    0.10
     Bau
    0.10
    scratch
    0.10
    chas
    0.10
    Activations Density 0.000%

    No Known Activations