© 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. 112690
    Prev
    Next
    INDEX
    Explanations

    boutique or niche businesses

    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
     kep
    -0.07
    EIF
    -0.07
     totally
    -0.07
     singleton
    -0.07
     tatto
    -0.07
     approximation
    -0.07
    hk
    -0.07
    usable
    -0.06
     halls
    -0.06
    wm
    -0.06
    POSITIVE LOGITS
    uru
    0.13
    /small
    0.13
    -sized
    0.12
    -style
    0.12
    chner
    0.11
     sized
    0.11
    stery
    0.11
    dale
    0.11
    ocha
    0.11
    attr
    0.11
    Activations Density 0.012%

    No Known Activations