© 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. 30363
    Prev
    Next
    INDEX
    Explanations

    grammar discussion

    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
     Bul
    -0.08
     ?.
    -0.08
     condensed
    -0.08
     shaken
    -0.08
     Ye
    -0.07
     tam
    -0.07
    erno
    -0.07
     Conte
    -0.07
     prio
    -0.07
    bul
    -0.07
    POSITIVE LOGITS
     [=
    0.17
     (=
    0.15
     .↵
    0.11
    ibi
    0.10
    sse
    0.10
     hur
    0.10
    usu
    0.09
     Morales
    0.09
     Dah
    0.09
    áºŃn
    0.09
    Activations Density 0.257%

    No Known Activations