© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52458
    Prev
    Next
    INDEX
    Explanations

    icopathologic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    -0.10
    loom
    -0.10
    oft
    -0.10
    ×
    -0.09
    éķ¿éĢĶ
    -0.09
    ClientId
    -0.09
    ãģĦãĤĭ
    -0.09
     lÆ°ng
    -0.09
    psilon
    -0.08
    åħ¨çIJĥæľĢ大
    -0.08
    POSITIVE LOGITS
    matic
    0.10
    opath
    0.10
    yen
    0.10
    rador
    0.09
    ÑĤÑĢи
    0.09
    orte
    0.09
    buster
    0.09
    agr
    0.09
    ForResource
    0.09
    ìĤ¬ìĿ´
    0.09
    Activations Density 0.040%

    No Known Activations