© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    worth doing well

    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
     Depths
    -0.09
     reloc
    -0.09
    rah
    -0.09
     fres
    -0.09
    itta
    -0.09
    eon
    -0.08
    hg
    -0.08
     democratic
    -0.08
    pe
    -0.08
    asia
    -0.08
    POSITIVE LOGITS
    adden
    0.11
    Filled
    0.11
    filled
    0.10
     Jub
    0.10
     Spending
    0.10
     oneself
    0.10
     wasting
    0.10
     Pad
    0.10
    /rem
    0.10
     spending
    0.10
    Activations Density 0.019%

    No Known Activations