© 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. 116352
    Prev
    Next
    INDEX
    Explanations

    shapes and suffixes

    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
    /st
    -0.10
     aver
    -0.09
    airs
    -0.09
    vore
    -0.08
     jap
    -0.08
    erner
    -0.08
    /se
    -0.08
    /pre
    -0.08
     tug
    -0.08
     hinter
    -0.08
    POSITIVE LOGITS
    -shaped
    0.20
     shaped
    0.19
     stands
    0.14
     shape
    0.13
    -word
    0.12
     Shapes
    0.12
     suffix
    0.12
     shapes
    0.12
     stood
    0.12
     letter
    0.12
    Activations Density 0.360%

    No Known Activations