© 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. 47237
    Prev
    Next
    INDEX
    Explanations

    I tried

    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
     unexpectedly
    -0.08
     бÑĥд
    -0.08
     abruptly
    -0.08
    iel
    -0.08
    pak
    -0.08
     knowingly
    -0.08
     emerging
    -0.08
     prematurely
    -0.07
     warmly
    -0.07
    Ny
    -0.07
    POSITIVE LOGITS
     tried
    0.43
     Tried
    0.38
     unsuccessfully
    0.35
     attempted
    0.34
     Attempts
    0.31
     attempts
    0.31
    Attempts
    0.29
     tries
    0.26
     unsuccessful
    0.24
    Attempt
    0.23
    Activations Density 1.622%

    No Known Activations