© 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. 47304
    Prev
    Next
    INDEX
    Explanations

    flex or flexion

    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
    liness
    -0.12
    aiser
    -0.10
    far
    -0.10
    riz
    -0.09
     wholesome
    -0.09
    à¸ļ
    -0.09
    лад
    -0.09
    icken
    -0.09
    elijke
    -0.09
     basket
    -0.09
    POSITIVE LOGITS
     muscles
    0.11
    uations
    0.10
     nostr
    0.09
    uates
    0.09
     Pav
    0.09
    uation
    0.09
     frost
    0.09
     Frid
    0.09
     against
    0.09
     disgr
    0.09
    Activations Density 0.001%

    No Known Activations