© 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. 50115
    Prev
    Next
    INDEX
    Explanations

    addicted, pattern, exile, fear, fix, thankful, changing, coupled, insidious, fire

    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
    uj
    -0.09
     Viv
    -0.08
     vant
    -0.08
     Macros
    -0.07
    uu
    -0.07
     tit
    -0.07
     versa
    -0.07
     bracket
    -0.07
     mou
    -0.07
     viv
    -0.07
    POSITIVE LOGITS
    .cc
    0.12
    775
    0.11
    .sap
    0.10
     Elias
    0.10
    mente
    0.10
    -less
    0.10
     Tor
    0.10
    oment
    0.10
     Ted
    0.10
    anca
    0.10
    Activations Density 0.405%

    No Known Activations