© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49428
    Prev
    Next
    INDEX
    Explanations

    home remedies or insecticides

    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
     smack
    -0.13
    amar
    -0.13
    iana
    -0.12
    amac
    -0.12
    904
    -0.12
     laten
    -0.12
    yg
    -0.11
     destruct
    -0.11
    ampaign
    -0.11
    ackages
    -0.11
    POSITIVE LOGITS
     Kear
    0.07
     IR
    0.07
     unbiased
    0.07
     MC
    0.07
     Rae
    0.07
     Hom
    0.06
    resa
    0.06
     round
    0.06
     Stap
    0.06
     nt
    0.06
    Activations Density 0.002%

    No Known Activations