© 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. 49632
    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
    -force
    -0.09
     drifting
    -0.09
    sek
    -0.08
    elson
    -0.08
     deleg
    -0.08
     ::=
    -0.08
     debris
    -0.08
    åĭķ
    -0.08
    ationally
    -0.07
     Broadway
    -0.07
    POSITIVE LOGITS
    soever
    0.11
     saber
    0.11
    /how
    0.10
    /if
    0.10
     Bender
    0.10
    achten
    0.10
    acht
    0.09
     */č↵č↵č↵
    0.09
     Pars
    0.09
     Poster
    0.09
    Activations Density 0.000%

    No Known Activations