© 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. 113058
    Prev
    Next
    INDEX
    Explanations

    names ending in 'y' or 'ie'

    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
    antic
    -0.08
    -0.08
    illy
    -0.08
     Clair
    -0.08
    ëĭ¤
    -0.08
     millennium
    -0.07
    ekt
    -0.07
    mes
    -0.07
    iew
    -0.07
    ilet
    -0.07
    POSITIVE LOGITS
    boro
    0.13
    anne
    0.12
    pond
    0.11
    odal
    0.10
    utions
    0.10
    ardon
    0.10
    ality
    0.09
    annes
    0.09
     mano
    0.09
     Ann
    0.09
    Activations Density 0.002%

    No Known Activations