© 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. 26653
    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
     immature
    -0.12
     incomplete
    -0.09
    irq
    -0.09
     pent
    -0.09
    choice
    -0.09
     Rin
    -0.08
     Screw
    -0.08
    processing
    -0.08
     dependencies
    -0.08
     authenticated
    -0.08
    POSITIVE LOGITS
     duk
    0.10
    /stretch
    0.09
     Collective
    0.09
     tran
    0.09
    olist
    0.09
    inge
    0.09
     sic
    0.09
     Kap
    0.09
     Bay
    0.09
    ieties
    0.09
    Activations Density 0.000%

    No Known Activations