© 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. 90516
    Prev
    Next
    INDEX
    Explanations

    genus *Mytilus*

    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
    uet
    -0.11
     cheek
    -0.10
    worthy
    -0.09
     lining
    -0.09
    ady
    -0.08
    XXX
    -0.08
     Ents
    -0.08
    ìĦ±
    -0.08
    ation
    -0.08
     nak
    -0.08
    POSITIVE LOGITS
     doom
    0.12
     sorts
    0.10
    summ
    0.10
    otto
    0.09
     woven
    0.09
    /App
    0.09
     destiny
    0.09
    udeau
    0.09
    ABS
    0.09
     Ages
    0.09
    Activations Density 0.096%

    No Known Activations