© 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. 17031
    Prev
    Next
    INDEX
    Explanations

    seriously neglected

    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
     JK
    -0.09
     preced
    -0.09
     Pun
    -0.08
     Thread
    -0.08
     fellow
    -0.08
     shy
    -0.08
     mitigation
    -0.08
     process
    -0.08
     merc
    -0.08
     Boolean
    -0.08
    POSITIVE LOGITS
     dirt
    0.17
     Dirt
    0.16
     dirty
    0.15
     sme
    0.14
    dirty
    0.14
     smell
    0.13
     saliva
    0.13
     smells
    0.13
     smelled
    0.13
     muddy
    0.13
    Activations Density 0.001%

    No Known Activations