© 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. 116131
    Prev
    Next
    INDEX
    Explanations

    resh, esh, ep, Beach, State

    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
    er
    -0.11
    rys
    -0.10
    EI
    -0.10
    âķIJ
    -0.09
    eon
    -0.09
     unp
    -0.09
     Ly
    -0.09
    RY
    -0.09
     frat
    -0.09
     unint
    -0.09
    POSITIVE LOGITS
    iola
    0.10
     Ultimately
    0.09
    дал
    0.09
     graz
    0.08
    cret
    0.08
    ed
    0.08
    enko
    0.08
    esome
    0.08
    /lic
    0.08
    -pencil
    0.08
    Activations Density 0.001%

    No Known Activations