© 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. 5061
    Prev
    Next
    INDEX
    Explanations

    socks and sock-related items

    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
    hire
    -0.12
    -ground
    -0.12
    hower
    -0.11
    loy
    -0.10
    hone
    -0.10
    hot
    -0.10
    oft
    -0.10
    oust
    -0.09
    zac
    -0.09
    zan
    -0.09
    POSITIVE LOGITS
    tober
    0.11
     socks
    0.11
    eed
    0.10
    ball
    0.10
    bean
    0.10
     stuffed
    0.10
     puppet
    0.10
    beans
    0.09
    _DGRAM
    0.09
    eel
    0.09
    Activations Density 0.005%

    No Known Activations