© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114488
    Prev
    Next
    INDEX
    Explanations

    not a

    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
    iture
    -0.08
    (Source
    -0.08
     Allison
    -0.08
     pled
    -0.07
    aler
    -0.07
    .kode
    -0.07
    oli
    -0.07
     Shirt
    -0.07
     expedition
    -0.07
     tempor
    -0.07
    POSITIVE LOGITS
     avid
    0.16
     coincidence
    0.15
     believer
    0.14
     supporter
    0.14
     aficion
    0.13
     resident
    0.13
     recipient
    0.13
     member
    0.13
     enthusiast
    0.13
     fan
    0.12
    Activations Density 0.049%

    No Known Activations