© 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. 28145
    Prev
    Next
    INDEX
    Explanations

    Callus

    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
    aged
    -0.10
    chu
    -0.08
    age
    -0.08
     devastation
    -0.08
     lipstick
    -0.08
    uc
    -0.08
    power
    -0.07
    éĢł
    -0.07
    è¾
    -0.07
    ight
    -0.07
    POSITIVE LOGITS
     bach
    0.12
     overriding
    0.12
     anunci
    0.12
     Fot
    0.10
    Sharper
    0.10
    /Page
    0.10
     outs
    0.10
    inals
    0.10
     Seventh
    0.10
     offs
    0.10
    Activations Density 0.002%

    No Known Activations