© 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. 116200
    Prev
    Next
    INDEX
    Explanations

    explaining how or why

    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
    fy
    -0.10
     Blanch
    -0.10
    HING
    -0.10
    éĽ
    -0.10
     Nom
    -0.09
    Also
    -0.09
     Tot
    -0.09
    $$$
    -0.09
    worthy
    -0.09
     Aad
    -0.09
    POSITIVE LOGITS
     why
    0.26
     how
    0.25
     what
    0.23
     Why
    0.22
     How
    0.20
     whats
    0.19
    Why
    0.19
     What
    0.19
    How
    0.18
    why
    0.18
    Activations Density 0.032%

    No Known Activations