© 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. 88622
    Prev
    Next
    INDEX
    Explanations

    aka

    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
     cet
    -0.11
     pist
    -0.10
    rab
    -0.10
    nad
    -0.09
    /the
    -0.09
    ä¿
    -0.09
     resent
    -0.09
     satur
    -0.09
     rebel
    -0.08
     definitive
    -0.08
    POSITIVE LOGITS
    allo
    0.11
    erer
    0.09
    otle
    0.08
     disproportion
    0.08
    esome
    0.08
    opro
    0.08
    /cgi
    0.08
     inval
    0.08
     []).
    0.08
     fore
    0.08
    Activations Density 0.002%

    No Known Activations