© 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. 111809
    Prev
    Next
    INDEX
    Explanations

    These followed by include or are

    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
     messed
    -0.09
    -type
    -0.09
     freeing
    -0.08
     reckon
    -0.08
    aml
    -0.08
     Knox
    -0.08
     Castle
    -0.08
     pers
    -0.08
     âĩ
    -0.08
     bastard
    -0.08
    POSITIVE LOGITS
     undergo
    0.12
     underwent
    0.10
     consists
    0.10
    riv
    0.10
    rive
    0.10
     consist
    0.10
    avin
    0.10
     served
    0.10
    aller
    0.10
     include
    0.10
    Activations Density 0.309%

    No Known Activations