© 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. 31581
    Prev
    Next
    INDEX
    Explanations

    Âł followed by a separator like $, DIS, [@, =, and

    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
    ward
    -0.09
    gil
    -0.08
    pare
    -0.08
    mo
    -0.08
    aign
    -0.08
    urt
    -0.08
     scape
    -0.08
     ineff
    -0.07
     vacancy
    -0.07
    ias
    -0.07
    POSITIVE LOGITS
    has
    0.10
    ãģ®
    0.10
     âĢº
    0.10
    @js
    0.10
    onto
    0.10
    (/
    0.10
    and
    0.09
    ».
    0.09
    was
    0.09
    ehen
    0.09
    Activations Density 0.051%

    No Known Activations