© 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. 50489
    Prev
    Next
    INDEX
    Explanations

    same time or sequence

    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
     until
    -0.10
     prob
    -0.09
    ument
    -0.09
    prob
    -0.09
     minlength
    -0.09
     equivalent
    -0.09
     forthcoming
    -0.09
     extrapol
    -0.09
     till
    -0.08
    until
    -0.08
    POSITIVE LOGITS
     simult
    0.26
     simultaneous
    0.26
     consec
    0.25
     simultaneously
    0.25
     consecutive
    0.24
     concurrently
    0.22
     sequentially
    0.21
     sequential
    0.20
     stagger
    0.19
     simul
    0.18
    Activations Density 0.298%

    No Known Activations