© 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. 4434
    Prev
    Next
    INDEX
    Explanations

    challenges, steps, stability, factors, implications, variations

    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
     lectures
    -0.09
    amac
    -0.08
    ometown
    -0.08
    agli
    -0.08
    :///
    -0.08
     goodness
    -0.08
     relaxed
    -0.08
    unde
    -0.08
    ework
    -0.08
    woods
    -0.08
    POSITIVE LOGITS
     pitfalls
    0.12
     [âĢ¦]↵↵
    0.12
     tips
    0.11
     considerations
    0.11
     afterward
    0.11
     FAQs
    0.11
     miscon
    0.11
     debunk
    0.10
     implications
    0.10
     [âĢ¦
    0.09
    Activations Density 1.324%

    No Known Activations