© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5565
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    IGN
    -0.08
     Mich
    -0.08
     Lov
    -0.08
    lev
    -0.08
    unset
    -0.08
    ات
    -0.08
    deen
    -0.08
     Morrow
    -0.07
     concession
    -0.07
     Reason
    -0.07
    POSITIVE LOGITS
     really
    0.41
     Really
    0.40
    Really
    0.38
    really
    0.37
     REALLY
    0.36
     realmente
    0.25
    羣
    0.24
     wirklich
    0.23
     Seriously
    0.23
     seriously
    0.22
    Activations Density 0.086%

    No Known Activations