© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    about

    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
     whether
    -0.11
    SEL
    -0.10
    nid
    -0.09
     fact
    -0.09
    &S
    -0.09
    ipel
    -0.09
    илÑĮ
    -0.09
    IMS
    -0.09
     Ville
    -0.09
    ights
    -0.09
    POSITIVE LOGITS
    erman
    0.09
     existence
    0.09
    egin
    0.09
    uku
    0.09
    RSS
    0.09
    ëĭ¹
    0.08
     contra
    0.08
    butt
    0.08
     forwarded
    0.08
     writ
    0.08
    Activations Density 0.055%

    No Known Activations