© 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. 32828
    Prev
    Next
    INDEX
    Explanations

    forewords, remarks, speeches, words

    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
     ÑģпиÑģ
    -0.10
     debates
    -0.10
     Names
    -0.10
     richness
    -0.10
     Reflex
    -0.09
     capital
    -0.09
     giorn
    -0.09
    isti
    -0.09
    Names
    -0.09
    esa
    -0.09
    POSITIVE LOGITS
     words
    0.36
     remarks
    0.35
     comments
    0.29
    words
    0.26
     remark
    0.26
     Remarks
    0.25
     Words
    0.25
     comment
    0.24
    Words
    0.23
    remarks
    0.22
    Activations Density 0.136%

    No Known Activations