© 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. 25622
    Prev
    Next
    INDEX
    Explanations

    others or populations

    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
     pare
    -0.10
    ixin
    -0.09
    arga
    -0.09
     amongst
    -0.09
    unge
    -0.08
     Desired
    -0.08
    iges
    -0.08
    ège
    -0.08
     :\
    -0.08
     altogether
    -0.08
    POSITIVE LOGITS
    /custom
    0.12
     myself
    0.11
     whom
    0.11
     wit
    0.11
    -custom
    0.10
    IEW
    0.10
     Mar
    0.10
     Wit
    0.10
    aux
    0.10
     Orig
    0.10
    Activations Density 0.274%

    No Known Activations