© 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. 115615
    Prev
    Next
    INDEX
    Explanations

    structure description or state

    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
     doctr
    -0.08
    uin
    -0.08
     automat
    -0.08
     Struct
    -0.08
     Ford
    -0.08
    Ford
    -0.08
    Mounted
    -0.08
     Mounted
    -0.08
     lev
    -0.08
     Bron
    -0.08
    POSITIVE LOGITS
     conducive
    0.18
     appealing
    0.13
     dictated
    0.13
     favorable
    0.13
     flattering
    0.12
     suited
    0.12
     pleasing
    0.12
    idar
    0.12
     exaggerated
    0.12
     env
    0.12
    Activations Density 0.308%

    No Known Activations