© 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. 48191
    Prev
    Next
    INDEX
    Explanations

    cadmium, Cadman, cadenza, cadet

    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
     dep
    -0.07
     reputation
    -0.06
     di
    -0.06
     impairment
    -0.06
     rain
    -0.06
     confess
    -0.06
     Ling
    -0.05
    cloud
    -0.05
     bew
    -0.05
    ike
    -0.05
    POSITIVE LOGITS
    caret
    0.14
    ritten
    0.13
    ÃŃcia
    0.13
    :\/\/
    0.12
    elles
    0.12
    ordes
    0.12
    issen
    0.12
    alist
    0.12
    esti
    0.12
    ampa
    0.12
    Activations Density 0.003%

    No Known Activations