© 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. 5043
    Prev
    Next
    INDEX
    Explanations

    LDH, LDL

    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
     intens
    -0.11
     hend
    -0.09
    ti
    -0.09
     sint
    -0.09
    æĦı
    -0.08
     intent
    -0.08
    OO
    -0.07
     thr
    -0.07
    illion
    -0.07
     accessory
    -0.07
    POSITIVE LOGITS
    quo
    0.17
    _LIBRARY
    0.13
    opa
    0.13
    osterone
    0.12
    uai
    0.11
    oce
    0.10
    른
    0.10
    ieurs
    0.10
     Beg
    0.10
    =en
    0.10
    Activations Density 0.091%

    No Known Activations