© 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. 116910
    Prev
    Next
    INDEX
    Explanations

    Puppet, Sesame, doll, require, fetch

    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
     datatable
    -0.10
     Apex
    -0.09
     samsung
    -0.09
     Caldwell
    -0.08
     Enums
    -0.08
    Stride
    -0.08
     lact
    -0.08
    azen
    -0.08
    ayan
    -0.08
     tiger
    -0.08
    POSITIVE LOGITS
     puppet
    0.25
     Puppet
    0.25
     pup
    0.18
    uppet
    0.16
     Ses
    0.16
     sesame
    0.15
     doll
    0.12
     dolls
    0.12
     Twe
    0.12
     Sculpt
    0.11
    Activations Density 0.824%

    No Known Activations