© 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. 49766
    Prev
    Next
    INDEX
    Explanations

    stuffing things into objects

    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
     Lance
    -0.11
     staple
    -0.09
    weep
    -0.09
    iendo
    -0.09
    ernen
    -0.09
     attention
    -0.09
    olta
    -0.09
     HIP
    -0.08
    LING
    -0.08
    909
    -0.08
    POSITIVE LOGITS
     stuffing
    0.13
     ballot
    0.13
     pockets
    0.13
     cram
    0.11
     pillows
    0.10
     altern
    0.10
     gaps
    0.10
    uffle
    0.10
    -full
    0.10
     into
    0.09
    Activations Density 0.013%

    No Known Activations