© 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. 26825
    Prev
    Next
    INDEX
    Explanations

    names followed by disambiguation

    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
    -if
    -0.10
    ","");↵
    -0.10
    âĢ¦the
    -0.09
    âĢ¦I
    -0.09
    -↵↵
    -0.08
    ---
    -0.08
    .�
    -0.08
    âĢ¦it
    -0.08
    alom
    -0.08
     ãĥ»
    -0.08
    POSITIVE LOGITS
     (/
    0.22
     (;
    0.18
    (/
    0.17
     redirects
    0.16
     abbreviated
    0.16
    styl
    0.15
    [a
    0.14
     shortened
    0.14
     styl
    0.14
     ("/
    0.13
    Activations Density 1.424%

    No Known Activations