© 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. 113155
    Prev
    Next
    INDEX
    Explanations

    licensed under apache license

    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
     sep
    -0.09
    ani
    -0.08
    sep
    -0.08
    aku
    -0.08
     µ
    -0.07
     Hyp
    -0.07
    marsh
    -0.07
     kiss
    -0.07
     vel
    -0.07
     suction
    -0.07
    POSITIVE LOGITS
    erb
    0.11
    jak
    0.11
    edin
    0.10
     Bent
    0.10
    eri
    0.10
     cud
    0.09
    _DP
    0.09
     uninterrupted
    0.09
     denomination
    0.09
    oyo
    0.09
    Activations Density 0.147%

    No Known Activations