© 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. 31903
    Prev
    Next
    INDEX
    Explanations

    excellent quality or craftsmanship

    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
    bie
    -0.12
    ually
    -0.11
    ful
    -0.11
    lessness
    -0.11
    cour
    -0.11
     decent
    -0.11
     handful
    -0.11
    land
    -0.11
     enormous
    -0.10
    dle
    -0.10
    POSITIVE LOGITS
     choice
    0.11
    -quality
    0.10
    -condition
    0.09
    adr
    0.09
    isp
    0.09
    choice
    0.09
     craftsmanship
    0.09
    -su
    0.09
     choices
    0.09
    istr
    0.08
    Activations Density 0.028%

    No Known Activations