© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    Kane or ane prefixes

    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
    anut
    -0.12
    phia
    -0.12
    eid
    -0.11
     parenthesis
    -0.11
    eon
    -0.10
    ahun
    -0.10
    ehr
    -0.10
    eyed
    -0.10
    steen
    -0.10
    eing
    -0.09
    POSITIVE LOGITS
    cek
    0.11
    fare
    0.09
    hower
    0.09
    ully
    0.08
    iac
    0.08
    esh
    0.08
    hattan
    0.08
     Programm
    0.08
    UIL
    0.08
    å¼ı
    0.08
    Activations Density 0.061%

    No Known Activations