© 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. 25906
    Prev
    Next
    INDEX
    Explanations

    smooth andfibrous andflawless eyes, more blendablesmooth muscle, fibroblastsFast Pacetexture and characteristicsflavor.smooth and fibsoften, flatten, and blanch

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     smooth
    -0.39
     Smooth
    -0.39
     smoothing
    -0.38
     smoother
    -0.37
    Smooth
    -0.36
     smoothed
    -0.36
    smooth
    -0.33
    _smooth
    -0.29
     smoothly
    -0.29
     softened
    -0.19
    POSITIVE LOGITS
     neutral
    0.09
     Monument
    0.09
     color
    0.08
     Burnett
    0.08
    wall
    0.07
     Ceiling
    0.07
     Gandhi
    0.07
    èĢ
    0.07
     liberal
    0.07
     slightly
    0.07
    Activations Density 0.109%

    No Known Activations