© 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. 15365
    Prev
    Next
    INDEX
    Explanations

    Give the phrase

    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
    oop
    -0.10
     Dudley
    -0.09
    NES
    -0.09
     Musik
    -0.09
     McCarthy
    -0.09
     nid
    -0.09
    912
    -0.09
     Soft
    -0.09
     Mata
    -0.08
    ania
    -0.08
    POSITIVE LOGITS
     me
    0.15
     yourself
    0.10
     Give
    0.10
    _me
    0.10
     datum
    0.10
     Yourself
    0.10
    Give
    0.10
     meis
    0.09
    me
    0.09
     Gor
    0.09
    Activations Density 0.011%

    No Known Activations