© 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. 17528
    Prev
    Next
    INDEX
    Explanations

    socket or socks

    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
     chains
    -0.11
     Pra
    -0.10
     platinum
    -0.10
     prm
    -0.10
     engraved
    -0.10
     alloy
    -0.10
     resin
    -0.09
     alloys
    -0.09
     vine
    -0.09
     cru
    -0.09
    POSITIVE LOGITS
     sock
    0.39
     socks
    0.37
    sock
    0.33
     SOCK
    0.31
    Sock
    0.31
    .sock
    0.23
     sockets
    0.23
    (sock
    0.22
     socket
    0.22
     Socket
    0.22
    Activations Density 0.106%

    No Known Activations