© 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. 32141
    Prev
    Next
    INDEX
    Explanations

    problems, questions, or statements

    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
     gist
    -0.11
    ippi
    -0.10
     Scope
    -0.10
     Boeh
    -0.10
    rieb
    -0.10
    CursorPosition
    -0.10
     originals
    -0.09
    tas
    -0.09
     tomorrow
    -0.09
     fil
    -0.09
    POSITIVE LOGITS
     unto
    0.15
     rather
    0.10
     disguised
    0.09
     disguise
    0.09
     waiting
    0.09
    atorium
    0.08
    ouser
    0.08
    rather
    0.08
    eten
    0.08
    orch
    0.08
    Activations Density 0.143%

    No Known Activations