© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113981
    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
     Fraser
    -0.10
     Frauen
    -0.10
     ticking
    -0.10
    ALT
    -0.10
    Inspect
    -0.10
     Newark
    -0.09
    atra
    -0.09
    usa
    -0.09
    lh
    -0.09
    atsu
    -0.09
    POSITIVE LOGITS
    pit
    0.09
     Norm
    0.08
     pit
    0.08
     bypass
    0.08
     doc
    0.08
     Splash
    0.08
    iju
    0.08
    /arch
    0.08
    boot
    0.07
     Goth
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.