© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    Natasha

    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
    oup
    -0.12
    chaft
    -0.11
    orp
    -0.11
    spr
    -0.10
    baum
    -0.10
    ELS
    -0.10
     DIR
    -0.10
    irie
    -0.10
    iction
    -0.10
    aber
    -0.10
    POSITIVE LOGITS
    sume
    0.12
    asha
    0.10
    ting
    0.09
    ters
    0.08
    _nat
    0.08
    stu
    0.08
    uality
    0.08
    zen
    0.08
    rous
    0.08
     Lands
    0.08
    Activations Density 0.003%

    No Known Activations