© 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. 33492
    Prev
    Next
    INDEX
    Explanations

    surfaces and entry points

    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
     Metro
    -0.11
    ness
    -0.11
     Shard
    -0.11
     irres
    -0.10
    Metro
    -0.10
    erness
    -0.10
     Strand
    -0.10
     Yam
    -0.10
     Sala
    -0.10
    Qt
    -0.09
    POSITIVE LOGITS
    weep
    0.12
     Bowen
    0.11
     entrance
    0.11
    /loading
    0.10
    arf
    0.09
     apr
    0.09
     Entrance
    0.09
     hoop
    0.09
     dug
    0.09
    /Gate
    0.09
    Activations Density 0.002%

    No Known Activations