© 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. 18318
    Prev
    Next
    INDEX
    Explanations

    shelf and bench contexts

    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
    kan
    -0.11
     Gst
    -0.10
     grounds
    -0.10
     Tin
    -0.10
     Conce
    -0.09
    /ne
    -0.09
    Lic
    -0.09
     Lyon
    -0.09
     Gover
    -0.09
    Views
    -0.09
    POSITIVE LOGITS
    /table
    0.15
    -top
    0.15
    -mounted
    0.13
    top
    0.13
    cloth
    0.12
    /platform
    0.12
    side
    0.12
    /column
    0.12
    ripsi
    0.10
    stead
    0.10
    Activations Density 0.252%

    No Known Activations