© 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. 26603
    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
     preceded
    -0.10
     compounded
    -0.10
     Invisible
    -0.10
     unlink
    -0.10
    EW
    -0.10
    nek
    -0.10
     trim
    -0.09
     precedent
    -0.09
    illard
    -0.09
     newsp
    -0.09
    POSITIVE LOGITS
     Sequ
    0.08
     scaling
    0.08
    sequ
    0.08
     bic
    0.08
     Simone
    0.08
    scaling
    0.08
     Coron
    0.08
     Instit
    0.08
     sequencing
    0.08
    oda
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.