© 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. 31410
    Prev
    Next
    INDEX
    Explanations

    treat and positive outcomes

    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
    airo
    -0.10
    cks
    -0.10
    aled
    -0.10
    grave
    -0.10
    .maximum
    -0.10
    onet
    -0.10
    ated
    -0.09
     Barnett
    -0.09
    gst
    -0.09
    RIES
    -0.09
    POSITIVE LOGITS
    ening
    0.13
    ments
    0.13
    ise
    0.12
    ened
    0.10
    ises
    0.09
    ement
    0.09
    asso
    0.09
    ize
    0.09
    iser
    0.09
    ãĥ¡ãĥ³ãĥĪ
    0.09
    Activations Density 0.064%

    No Known Activations