© 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. 115381
    Prev
    Next
    INDEX
    Explanations

    HTML tags like `&#` and `<br`

    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
    ÙĴ
    -0.12
    ape
    -0.11
    är
    -0.11
    оÑģÑĮ
    -0.11
    دÙĬ
    -0.11
     appreh
    -0.10
    eq
    -0.10
    asha
    -0.10
    约
    -0.10
    ej
    -0.10
    POSITIVE LOGITS
    CDATA
    0.11
    s
    0.08
     nowhere
    0.08
     Blond
    0.08
    ird
    0.08
    xad
    0.07
    sed
    0.07
    ably
    0.07
    byss
    0.07
    809
    0.07
    Activations Density 0.073%

    No Known Activations