© 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. 113417
    Prev
    Next
    INDEX
    Explanations

    if the

    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
     herself
    -0.13
     spontaneously
    -0.12
     âĿ¤
    -0.12
    .She
    -0.12
     —↵↵
    -0.12
     her
    -0.11
    linked
    -0.11
    (Content
    -0.11
    _GB
    -0.11
     incompatible
    -0.11
    POSITIVE LOGITS
     kn
    0.09
     forcing
    0.09
     forces
    0.08
     pressing
    0.08
     tightening
    0.08
     tight
    0.08
     cant
    0.08
     sloppy
    0.08
    ansa
    0.07
     flex
    0.07
    Activations Density 5.253%

    No Known Activations