© 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. 47176
    Prev
    Next
    INDEX
    Explanations

    customer, client, or consumer

    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
     debuted
    -0.10
     embody
    -0.10
    chk
    -0.10
     sell
    -0.10
     strife
    -0.10
    isin
    -0.09
    gh
    -0.09
     embodies
    -0.09
     selling
    -0.09
    he
    -0.09
    POSITIVE LOGITS
    /con
    0.12
    /user
    0.11
     purchasing
    0.11
    /users
    0.11
     buying
    0.10
     visiting
    0.10
     PAY
    0.10
    /custom
    0.10
    /Users
    0.10
    /rec
    0.10
    Activations Density 0.071%

    No Known Activations