© 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. 47699
    Prev
    Next
    INDEX
    Explanations

    jean followed by names

    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
    aler
    -0.10
     occasion
    -0.09
    tober
    -0.09
    odings
    -0.08
     informational
    -0.08
    gew
    -0.08
     Chill
    -0.08
    imir
    -0.08
    аÑĤÑĮ
    -0.08
    gger
    -0.08
    POSITIVE LOGITS
    ne
    0.17
    ette
    0.15
    iene
    0.13
     Claude
    0.13
    mar
    0.12
    -P
    0.12
    ichel
    0.12
    -Mar
    0.11
     Bapt
    0.11
    bart
    0.11
    Activations Density 0.029%

    No Known Activations