© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    whipped cream, icing, pie

    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
     mud
    -0.12
     Clay
    -0.11
     Sands
    -0.11
     sands
    -0.10
     clay
    -0.10
     Mud
    -0.10
     lizard
    -0.10
     sand
    -0.10
     jade
    -0.09
     rubble
    -0.09
    POSITIVE LOGITS
     whipping
    0.18
     whip
    0.17
     whipped
    0.17
     Whip
    0.16
     Decorating
    0.14
     decorating
    0.13
     frosting
    0.12
     icing
    0.12
    /ic
    0.12
     piping
    0.12
    Activations Density 0.024%

    No Known Activations