© 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. 115485
    Prev
    Next
    INDEX
    Explanations

    project or 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
     ...\
    -0.09
     succeeds
    -0.09
     [:
    -0.09
    /Images
    -0.08
    ViewController
    -0.08
     precious
    -0.08
    {*
    -0.08
    ,but
    -0.08
     Antar
    -0.08
    ault
    -0.08
    POSITIVE LOGITS
     which
    0.35
    —a
    0.34
    —which
    0.33
    which
    0.33
    —an
    0.30
     WHICH
    0.25
     wich
    0.24
    (which
    0.23
     коÑĤоÑĢÑĭй
    0.22
     Which
    0.19
    Activations Density 2.464%

    No Known Activations