© 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. 5294
    Prev
    Next
    INDEX
    Explanations

    into being, into the, in the

    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
    iza
    -0.08
    mor
    -0.08
     struggling
    -0.07
     Belly
    -0.07
    mare
    -0.07
     recess
    -0.07
    Ìģ
    -0.07
    ress
    -0.07
    _font
    -0.07
     Font
    -0.07
    POSITIVE LOGITS
     skin
    0.25
     skins
    0.21
    skin
    0.19
     Skin
    0.18
    Skin
    0.18
     oneself
    0.17
    身
    0.16
    skins
    0.15
    _skin
    0.15
    .skin
    0.15
    Activations Density 0.055%

    No Known Activations