© 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. 115875
    Prev
    Next
    INDEX
    Explanations

    wild

    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
    annah
    -0.09
     Sunny
    -0.08
     Uni
    -0.08
     mog
    -0.08
    /es
    -0.08
     CA
    -0.08
    ket
    -0.08
    ariat
    -0.08
     Parker
    -0.08
    sse
    -0.08
    POSITIVE LOGITS
     wild
    0.18
    wild
    0.16
    Wild
    0.15
     Wild
    0.14
     wildcard
    0.12
    ild
    0.11
     Wilde
    0.11
     wildfire
    0.10
    opr
    0.10
    Wildcard
    0.10
    Activations Density 0.001%

    No Known Activations