© 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. 113055
    Prev
    Next
    INDEX
    Explanations

    choosing best business outcomes

    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
     VERY
    -0.10
     very
    -0.10
     menn
    -0.09
     (?)
    -0.09
    úa
    -0.09
    Republicans
    -0.09
    ìŀħëĭĪëĭ¤
    -0.09
     Watches
    -0.09
    inite
    -0.09
    asm
    -0.09
    POSITIVE LOGITS
     oneself
    0.23
     yourself
    0.15
     isn
    0.13
     involves
    0.13
    -any
    0.12
     blindly
    0.12
     anything
    0.12
    anything
    0.12
    ients
    0.12
     alone
    0.12
    Activations Density 0.782%

    No Known Activations