© 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. 5902
    Prev
    Next
    INDEX
    Explanations

    score board

    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
     over
    -0.12
    #/
    -0.09
    è¿ĩ
    -0.09
     Over
    -0.09
    171
    -0.08
    Over
    -0.08
    ",-
    -0.08
    station
    -0.08
     reopened
    -0.08
     singled
    -0.08
    POSITIVE LOGITS
     |
    0.35
    |
    0.32
    |x
    0.26
    |(
    0.23
    |\
    0.23
    |M
    0.23
    |RF
    0.23
    |m
    0.23
     |\
    0.23
    |r
    0.22
    Activations Density 0.137%

    No Known Activations