© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5327
    Prev
    Next
    INDEX
    Explanations

    purchasing and purchase decisions

    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
    onta
    -0.12
    rud
    -0.09
     ime
    -0.09
    ieme
    -0.09
     flaw
    -0.09
    ima
    -0.09
     Morg
    -0.09
     Harden
    -0.09
     flawless
    -0.09
    imi
    -0.09
    POSITIVE LOGITS
    eland
    0.11
    -controls
    0.09
     dips
    0.09
    rez
    0.09
     Av
    0.09
    poss
    0.09
     Clown
    0.08
    Checkout
    0.08
     Wort
    0.08
    978
    0.08
    Activations Density 0.003%

    No Known Activations