© 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. 113437
    Prev
    Next
    INDEX
    Explanations

    phthalic acid and derivatives

    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
    kap
    -0.09
    ewing
    -0.09
     Kap
    -0.09
     Dana
    -0.08
    /disc
    -0.08
    ohon
    -0.08
     Urb
    -0.08
     clo
    -0.08
     clos
    -0.08
    flix
    -0.08
    POSITIVE LOGITS
     whale
    0.13
    deaux
    0.10
     overs
    0.10
     dau
    0.10
    HING
    0.10
     Norte
    0.10
     cres
    0.10
    zar
    0.10
    eos
    0.10
     honor
    0.10
    Activations Density 0.002%

    No Known Activations