© 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. 29875
    Prev
    Next
    INDEX
    Explanations

    velvet, smooth, silky, sandy, crystal, golden, ruby

    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
    heim
    -0.11
    aza
    -0.10
    ries
    -0.10
    CMP
    -0.10
    ody
    -0.10
     Bust
    -0.09
     clutter
    -0.09
    ota
    -0.09
    Bind
    -0.09
    phasis
    -0.09
    POSITIVE LOGITS
    -like
    0.18
     smooth
    0.18
    -sm
    0.16
    smooth
    0.14
     Smooth
    0.13
    Smooth
    0.12
     smoother
    0.12
    -text
    0.11
     smoothly
    0.10
    _smooth
    0.10
    Activations Density 0.010%

    No Known Activations