© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    wordpress.org/?v=

    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
     proport
    -0.12
    romo
    -0.11
     Sle
    -0.10
     tod
    -0.10
     roku
    -0.10
     lite
    -0.10
    aggio
    -0.10
    chas
    -0.10
    onor
    -0.10
     slee
    -0.10
    POSITIVE LOGITS
     danger
    0.08
    amage
    0.08
    wart
    0.08
    kit
    0.08
    Tumblr
    0.07
    eur
    0.07
     assert
    0.07
     pseudo
    0.07
    acz
    0.07
     pseud
    0.07
    Activations Density 0.009%

    No Known Activations