© 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. 48214
    Prev
    Next
    INDEX
    Explanations

    held down

    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
    mina
    -0.10
    isy
    -0.09
     pace
    -0.09
     scatter
    -0.09
    eba
    -0.08
    kos
    -0.08
     speeding
    -0.08
     leaps
    -0.08
     interp
    -0.08
     dich
    -0.08
    POSITIVE LOGITS
     duration
    0.24
     lasted
    0.22
     Duration
    0.22
     linger
    0.22
     durations
    0.21
    duration
    0.21
     held
    0.21
    Duration
    0.20
     prolonged
    0.20
     hold
    0.20
    Activations Density 0.050%

    No Known Activations