© 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. 115252
    Prev
    Next
    INDEX
    Explanations

    community guidelines

    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
    vit
    -0.10
    ifen
    -0.09
     Vit
    -0.09
    oba
    -0.09
     Barrel
    -0.08
     neo
    -0.08
    oren
    -0.08
     tandem
    -0.08
    strap
    -0.08
    onom
    -0.08
    POSITIVE LOGITS
     subgroup
    0.11
     GAP
    0.09
     ens
    0.09
     rag
    0.08
    Wizard
    0.08
     granny
    0.08
     charter
    0.08
    TestFixture
    0.08
    /member
    0.08
     flo
    0.08
    Activations Density 1.636%

    No Known Activations