© 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. 113628
    Prev
    Next
    INDEX
    Explanations

    shows descriptions of actions or data

    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
    oft
    -0.08
    anje
    -0.08
     Locke
    -0.08
     dul
    -0.08
    unic
    -0.08
     *}
    -0.08
     Anglo
    -0.08
     rot
    -0.08
    ty
    -0.07
     thriving
    -0.07
    POSITIVE LOGITS
     rather
    0.15
    rather
    0.13
     Rather
    0.12
    movement
    0.12
    Rather
    0.11
     movement
    0.11
     exh
    0.11
     plutôt
    0.11
     tension
    0.11
     Sandbox
    0.11
    Activations Density 0.004%

    No Known Activations