© 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. 32668
    Prev
    Next
    INDEX
    Explanations

    you mean

    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
    ras
    -0.11
     Hab
    -0.11
    lu
    -0.10
     balanced
    -0.10
     tricky
    -0.09
     Argument
    -0.09
    uko
    -0.09
    ruk
    -0.09
    ubi
    -0.09
     preferences
    -0.09
    POSITIVE LOGITS
     talking
    0.16
     talk
    0.13
     Talking
    0.12
     talks
    0.10
     drunken
    0.10
    -talk
    0.09
    talk
    0.09
    chia
    0.09
     Alleg
    0.09
     strangely
    0.09
    Activations Density 0.012%

    No Known Activations