© 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. 4333
    Prev
    Next
    INDEX
    Explanations

    should not

    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
    kan
    -0.10
     however
    -0.09
     Ay
    -0.09
    ior
    -0.09
    iete
    -0.09
    ennon
    -0.09
     wre
    -0.09
    udging
    -0.09
     Bol
    -0.09
     Verm
    -0.09
    POSITIVE LOGITS
     McA
    0.10
     Nikola
    0.09
     tit
    0.09
    QN
    0.09
    ategory
    0.09
    bern
    0.09
    елÑı
    0.08
    cul
    0.08
     org
    0.08
     Gaw
    0.08
    Activations Density 0.116%

    No Known Activations