© 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. 49005
    Prev
    Next
    INDEX
    Explanations

    am, amend, ammon, amph

    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
     Arabia
    -0.09
    atan
    -0.09
    /authentication
    -0.09
    iers
    -0.08
    ques
    -0.08
    imenti
    -0.08
    ually
    -0.08
    ernal
    -0.08
    PAR
    -0.08
    lings
    -0.08
    POSITIVE LOGITS
    ERICAN
    0.16
    ethyst
    0.16
    sterdam
    0.14
    amation
    0.12
    nesia
    0.12
     besten
    0.12
    /am
    0.12
    /pm
    0.12
    usement
    0.11
    oxic
    0.11
    Activations Density 0.234%

    No Known Activations