© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37071
    Prev
    Next
    INDEX
    Explanations

    passed away

    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
     ë¶Ī구íķĺê³ł
    -0.10
    ected
    -0.09
    stalk
    -0.09
    ested
    -0.08
    egration
    -0.08
    ús
    -0.08
    _war
    -0.08
     Freak
    -0.08
    è¡Įäºĭ
    -0.08
    èµĦ
    -0.08
    POSITIVE LOGITS
    sword
    0.11
    iap
    0.09
    èĪªæµ·
    0.09
    own
    0.09
     mere
    0.08
    plr
    0.08
    éĤ£ä½į
    0.08
    æĮĩ导æĦıè§ģ
    0.08
    mani
    0.08
     ACLU
    0.08
    Activations Density 0.002%

    No Known Activations