© 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. 114516
    Prev
    Next
    INDEX
    Explanations

    K followed by specific suffixes

    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
    Kind
    -0.12
     kind
    -0.12
    oux
    -0.12
    ej
    -0.11
    -kind
    -0.10
     KIND
    -0.10
    ez
    -0.10
    addin
    -0.10
    icos
    -0.10
     Kind
    -0.10
    POSITIVE LOGITS
    ế
    0.11
    aepernick
    0.11
    chief
    0.09
    pow
    0.09
    haled
    0.09
    ematics
    0.09
    nap
    0.09
    rypton
    0.08
    urahan
    0.08
    dims
    0.08
    Activations Density 0.396%

    No Known Activations