© 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. 113449
    Prev
    Next
    INDEX
    Explanations

    tightly coupled or controlled

    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
     Tos
    -0.11
     doubt
    -0.10
    aeda
    -0.09
    cea
    -0.09
     forth
    -0.08
    ickle
    -0.08
     fatt
    -0.08
    eri
    -0.08
     loudly
    -0.08
    pite
    -0.08
    POSITIVE LOGITS
    ening
    0.22
    ened
    0.19
    est
    0.18
    ness
    0.18
     knit
    0.16
    ener
    0.14
    ens
    0.13
    rop
    0.13
    (er
    0.13
    -k
    0.12
    Activations Density 0.014%

    No Known Activations