© 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. 89991
    Prev
    Next
    INDEX
    Explanations

    why

    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
    872
    -0.09
    IGO
    -0.09
    BS
    -0.09
    onus
    -0.09
    owo
    -0.08
    igo
    -0.08
    vier
    -0.08
    AGO
    -0.08
    /AP
    -0.08
     lagi
    -0.08
    POSITIVE LOGITS
     Cory
    0.13
     Marsh
    0.11
     Marshal
    0.10
     vit
    0.10
     Marshall
    0.10
    228
    0.10
     Diss
    0.10
     strategically
    0.10
     autob
    0.09
     Savannah
    0.09
    Activations Density 0.009%

    No Known Activations