© 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. 117050
    Prev
    Next
    INDEX
    Explanations

    names starting with 'Ka' or 'Cat'

    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
     toss
    -0.10
     kre
    -0.10
     intra
    -0.09
     tossing
    -0.09
    kip
    -0.09
    quier
    -0.09
     oath
    -0.09
     serpent
    -0.09
    igel
    -0.09
    à¹
    -0.09
    POSITIVE LOGITS
     mou
    0.10
     stiff
    0.10
     Cata
    0.10
     kittens
    0.09
    añ
    0.09
     Locker
    0.09
     Cater
    0.09
     Cath
    0.09
    -corner
    0.09
     Contest
    0.09
    Activations Density 0.067%

    No Known Activations