© 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. 31190
    Prev
    Next
    INDEX
    Explanations

    utility or associated term

    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
    usp
    -0.08
     caut
    -0.08
    /Branch
    -0.08
    ,',
    -0.07
     offs
    -0.07
    (TM
    -0.07
    /***/
    -0.07
    Readable
    -0.07
     nues
    -0.07
     incred
    -0.06
    POSITIVE LOGITS
     everywhere
    0.17
     awaits
    0.16
     apl
    0.16
     isn
    0.15
     abound
    0.15
     without
    0.15
     gal
    0.15
     occurs
    0.15
     Everywhere
    0.14
     forever
    0.14
    Activations Density 0.309%

    No Known Activations