© 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. 111771
    Prev
    Next
    INDEX
    Explanations

    names ending in k, ek, or sk

    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
     Maur
    -0.09
     hoops
    -0.09
     twig
    -0.08
    ierre
    -0.08
     ks
    -0.08
     rarity
    -0.08
     kenn
    -0.08
     Loud
    -0.08
     aloud
    -0.08
     loud
    -0.08
    POSITIVE LOGITS
    ingen
    0.10
    onium
    0.10
     unidentified
    0.10
    inka
    0.10
    una
    0.10
     unilateral
    0.09
    sterol
    0.09
    -inline
    0.09
     PUSH
    0.09
    pine
    0.09
    Activations Density 0.001%

    No Known Activations