© 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. 49967
    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
    izador
    -0.10
     cascade
    -0.10
    oom
    -0.10
     Trio
    -0.10
    arel
    -0.10
     intercepted
    -0.10
     Shaun
    -0.09
     repl
    -0.09
    vary
    -0.09
     Eid
    -0.09
    POSITIVE LOGITS
     ordering
    0.10
     LOCATION
    0.08
    ymph
    0.08
     crashing
    0.08
    åľŁ
    0.08
     Ring
    0.08
     location
    0.08
     coupled
    0.07
    lico
    0.07
     ((!
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.