© 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. 48498
    Prev
    Next
    INDEX
    Explanations

    delicate balance or sequence

    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
     Stap
    -0.10
     comfy
    -0.10
     defiant
    -0.09
     stor
    -0.09
     Astr
    -0.09
    ber
    -0.09
    edList
    -0.09
    ionic
    -0.09
    ed
    -0.09
     Ler
    -0.09
    POSITIVE LOGITS
     delicate
    0.20
     balance
    0.17
     Balance
    0.16
     delic
    0.15
     balances
    0.13
     fragile
    0.13
    Balance
    0.12
    zza
    0.12
    balance
    0.12
    ately
    0.11
    Activations Density 0.009%

    No Known Activations