© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    seeking you

    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
     targeted
    -0.08
     intuit
    -0.08
    ê¸
    -0.08
    /I
    -0.08
    screen
    -0.08
     Vend
    -0.07
     scrap
    -0.07
     Catalog
    -0.07
     guit
    -0.07
     tee
    -0.07
    POSITIVE LOGITS
     Busy
    0.11
     wont
    0.10
    stroy
    0.10
    aret
    0.10
     disfr
    0.10
    aec
    0.10
     multic
    0.10
    anter
    0.10
     Citation
    0.09
    unic
    0.09
    Activations Density 0.002%

    No Known Activations