© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 47063
    Prev
    Next
    INDEX
    Explanations

    causes or results in

    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
     thats
    -0.14
     ÑįÑĤо
    -0.13
    >this
    -0.10
    ernet
    -0.10
     this
    -0.10
     nevertheless
    -0.10
    )this
    -0.10
    —a
    -0.09
    :this
    -0.09
    —that
    -0.09
    POSITIVE LOGITS
     firstly
    0.09
     notwithstanding
    0.09
     unfortunate
    0.09
    ERIC
    0.08
     lle
    0.08
    loff
    0.08
     McInt
    0.08
     aside
    0.08
    mani
    0.08
     especially
    0.08
    Activations Density 0.440%

    No Known Activations