© 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. 15605
    Prev
    Next
    INDEX
    Explanations

    which

    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
    amer
    -0.09
    yas
    -0.08
    339
    -0.08
    ou
    -0.08
     ps
    -0.08
     IMM
    -0.08
     Ank
    -0.08
     cuz
    -0.08
    ãģŁãģł
    -0.08
     appart
    -0.08
    POSITIVE LOGITS
    —which
    0.39
     which
    0.26
    which
    0.24
    —an
    0.21
    —a
    0.20
     WHICH
    0.19
    (which
    0.19
    Which
    0.19
     Which
    0.18
     wich
    0.16
    Activations Density 1.838%

    No Known Activations