© 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. 90939
    Prev
    Next
    INDEX
    Explanations

    reliability of

    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
     Nag
    -0.07
     sa
    -0.06
    à¸ģร
    -0.06
     IS
    -0.06
    tems
    -0.06
     wed
    -0.06
     Parm
    -0.06
     Wed
    -0.06
    Callbacks
    -0.06
     Wes
    -0.06
    POSITIVE LOGITS
    owl
    0.12
     Baum
    0.11
     Kushner
    0.11
     loosen
    0.11
    ëĭ¹
    0.11
    stor
    0.10
     dossier
    0.10
     anyways
    0.10
     Fucking
    0.10
     accus
    0.10
    Activations Density 1.595%

    No Known Activations