© 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. 90364
    Prev
    Next
    INDEX
    Explanations

    ä¸ĢäºĽ

    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
     Floyd
    -0.10
     Platt
    -0.10
     exponentially
    -0.10
    ienie
    -0.09
     em
    -0.09
     exponential
    -0.09
    fair
    -0.09
    isko
    -0.09
     mé
    -0.09
    att
    -0.09
    POSITIVE LOGITS
    äºĽ
    0.14
    trer
    0.09
     abortions
    0.09
    rema
    0.09
    aroo
    0.09
    XL
    0.09
    OTS
    0.09
    aska
    0.09
    lrt
    0.09
    ี
    0.09
    Activations Density 0.004%

    No Known Activations