© 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. 89693
    Prev
    Next
    INDEX
    Explanations

    // Distributed license

    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
     mixture
    -0.12
     Sle
    -0.11
     minib
    -0.10
     perverse
    -0.10
     kino
    -0.10
    abe
    -0.10
     distracted
    -0.10
    erable
    -0.10
     latent
    -0.10
    tee
    -0.09
    POSITIVE LOGITS
     sketch
    0.08
     unnamed
    0.08
    DR
    0.07
    ahir
    0.07
    _DS
    0.07
     DR
    0.07
    axes
    0.07
     stead
    0.07
     smash
    0.07
    472
    0.07
    Activations Density 0.001%

    No Known Activations