© 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. 32408
    Prev
    Next
    INDEX
    Explanations

    hedge hog

    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
     sack
    -0.12
    chy
    -0.11
    lest
    -0.11
     Coh
    -0.11
    oved
    -0.11
    onta
    -0.11
    oa
    -0.10
    ses
    -0.10
     exponentially
    -0.10
    iry
    -0.10
    POSITIVE LOGITS
    hog
    0.23
     hedge
    0.15
     hed
    0.13
     Hedge
    0.13
     Hed
    0.12
    cock
    0.11
     fence
    0.11
     fences
    0.10
     bet
    0.10
     hog
    0.09
    Activations Density 0.046%

    No Known Activations