© 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. 48869
    Prev
    Next
    INDEX
    Explanations

    signs, when, person, law, carbon, depth, construction

    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
     Fortunately
    -0.12
     leider
    -0.11
    Fortunately
    -0.10
     lifestyle
    -0.10
    ocol
    -0.10
     Lifestyle
    -0.10
    BLE
    -0.10
     maj
    -0.10
     Foster
    -0.09
     peru
    -0.09
    POSITIVE LOGITS
     when
    0.11
     subconscious
    0.11
     definitely
    0.11
     invol
    0.10
     especially
    0.10
     canon
    0.10
     consciously
    0.10
     When
    0.09
     uncon
    0.09
    when
    0.09
    Activations Density 0.013%

    No Known Activations