© 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. 5603
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    uma
    -0.10
    ahi
    -0.10
    inp
    -0.09
    owi
    -0.09
    orp
    -0.09
     Emerson
    -0.09
    isser
    -0.08
    329
    -0.08
    berger
    -0.08
    abb
    -0.08
    POSITIVE LOGITS
     including
    0.75
     Including
    0.67
    —including
    0.64
    including
    0.63
     INCLUDING
    0.62
    Including
    0.60
    INCLUDING
    0.45
     includ
    0.38
    cluding
    0.35
     incl
    0.31
    Activations Density 2.046%

    No Known Activations