© 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. 88801
    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
     snatch
    -0.10
    (access
    -0.10
    ventus
    -0.10
    erness
    -0.10
     hungry
    -0.09
     impe
    -0.09
    indi
    -0.09
     inclined
    -0.09
     crunch
    -0.09
    onaut
    -0.09
    POSITIVE LOGITS
    mour
    0.09
    Bang
    0.09
     alongside
    0.08
    mess
    0.08
    /t
    0.08
     ro
    0.08
     Tango
    0.08
     afterward
    0.08
    ROM
    0.07
     serv
    0.07
    Activations Density 0.000%

    No Known Activations