© 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. 15777
    Prev
    Next
    INDEX
    Explanations

    werewolf

    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
    amento
    -0.10
    Govern
    -0.09
    mund
    -0.09
    ihn
    -0.09
     denn
    -0.08
    amenti
    -0.08
    aire
    -0.08
    needle
    -0.08
    eyed
    -0.08
    cido
    -0.08
    POSITIVE LOGITS
    bows
    0.10
    uche
    0.10
    chan
    0.10
    ewolf
    0.10
    bare
    0.10
     bare
    0.10
     stap
    0.09
     pitched
    0.09
    osta
    0.09
    EW
    0.09
    Activations Density 0.012%

    No Known Activations