© 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. 32651
    Prev
    Next
    INDEX
    Explanations

    diagnosis

    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
    idth
    -0.10
    arra
    -0.10
    Investigators
    -0.09
     chees
    -0.09
    otime
    -0.09
     Cheese
    -0.08
     prosec
    -0.08
    arth
    -0.08
     Carp
    -0.08
    ORN
    -0.08
    POSITIVE LOGITS
     diagn
    0.38
     diagnosis
    0.37
     diagnose
    0.36
     diagnoses
    0.33
     Diagnosis
    0.33
     diagnosed
    0.31
     diagnostics
    0.30
     diagnostic
    0.28
     diag
    0.24
     Diagnostic
    0.22
    Activations Density 0.853%

    No Known Activations