© 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. 28488
    Prev
    Next
    INDEX
    Explanations

    pop and popliteal

    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
     unearth
    -0.09
    fork
    -0.08
     Canter
    -0.08
    TC
    -0.08
    amble
    -0.07
     bargain
    -0.07
     sto
    -0.07
    passport
    -0.07
     Centro
    -0.07
     unh
    -0.07
    POSITIVE LOGITS
     Pop
    0.22
    Pop
    0.20
     pop
    0.19
    /pop
    0.17
     POP
    0.15
    _pop
    0.15
     popping
    0.15
     popped
    0.15
    .Pop
    0.15
    ipop
    0.15
    Activations Density 0.100%

    No Known Activations