© 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. 116294
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
     legit
    -0.12
    (Py
    -0.11
     Cond
    -0.11
     mans
    -0.10
     Lens
    -0.10
    WWW
    -0.10
    ubo
    -0.10
     enlight
    -0.10
    eus
    -0.10
     Durch
    -0.10
    POSITIVE LOGITS
     fictional
    0.08
     postcode
    0.08
     serial
    0.08
    owa
    0.08
     Hay
    0.08
    lis
    0.07
    lias
    0.07
     Sed
    0.07
     waking
    0.07
     Colbert
    0.07
    Activations Density 0.005%

    No Known Activations