© 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. 17480
    Prev
    Next
    INDEX
    Explanations

    related to topics

    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
    isten
    -0.09
    ,user
    -0.09
     INA
    -0.09
     Mug
    -0.09
     impatient
    -0.09
     Contr
    -0.09
     indem
    -0.09
    tha
    -0.09
    gn
    -0.09
    olie
    -0.09
    POSITIVE LOGITS
    -related
    0.25
     related
    0.17
    _related
    0.16
    缸åħ³
    0.16
    related
    0.15
    -centric
    0.15
     Related
    0.15
    -based
    0.15
    -themed
    0.14
    -oriented
    0.13
    Activations Density 2.062%

    No Known Activations