© 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. 15864
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    稿
    -0.10
    inha
    -0.10
     moderator
    -0.09
    foundation
    -0.08
    ardin
    -0.08
    abi
    -0.08
     abnormal
    -0.08
    dif
    -0.08
     Sob
    -0.08
     faculties
    -0.08
    POSITIVE LOGITS
     Trot
    0.10
     lug
    0.09
     Gret
    0.09
     overs
    0.09
    ijn
    0.09
     teh
    0.09
     opportunity
    0.09
     Fa
    0.09
     Grip
    0.09
    ippers
    0.09
    Activations Density 0.000%

    No Known Activations