© 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. 6454
    Prev
    Next
    INDEX
    Explanations

    seems like

    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
     zd
    -0.11
     Pall
    -0.11
     cél
    -0.11
     filmer
    -0.10
    ãģĹãģĭ
    -0.10
    /utility
    -0.10
    opaque
    -0.10
    Ein
    -0.09
     nicknamed
    -0.09
     cz
    -0.09
    POSITIVE LOGITS
     there
    0.21
    there
    0.16
     everytime
    0.13
     every
    0.13
     it
    0.13
     everyone
    0.12
     they
    0.12
     we
    0.12
     everybody
    0.12
     whenever
    0.12
    Activations Density 0.018%

    No Known Activations