© 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. 27619
    Prev
    Next
    INDEX
    Explanations

    sun[ ]beds/sets/Rail/exposed/roof/ken

    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
     Burb
    -0.10
     serr
    -0.09
     McDonald
    -0.09
     Campo
    -0.08
    ENCY
    -0.08
    ifers
    -0.08
    ortho
    -0.08
    cimal
    -0.08
    ental
    -0.08
    ANT
    -0.08
    POSITIVE LOGITS
    ken
    0.16
    flower
    0.15
    burn
    0.13
     vit
    0.12
     bathing
    0.11
     worsh
    0.11
     tolerance
    0.11
    bat
    0.11
    stroke
    0.11
     loung
    0.11
    Activations Density 0.008%

    No Known Activations