© 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. 52816
    Prev
    Next
    INDEX
    Explanations

    programmed cell death

    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
    åľ°ä½į
    -0.10
    åĽ½æĥħ
    -0.09
    åĵģä½į
    -0.09
    otch
    -0.09
     ÐĽÐ°
    -0.09
    rador
    -0.09
    éĬ
    -0.08
    astr
    -0.08
    anted
    -0.08
    NCY
    -0.08
    POSITIVE LOGITS
    ä¸įæŃ»
    0.11
    身亡
    0.09
     apoptosis
    0.09
    å°ķ
    0.09
    è¿Ļçīĩ
    0.09
     die
    0.09
    æŃ»
    0.09
     death
    0.09
    æŃ»åĪij
    0.09
    æŃ»èĢħ
    0.08
    Activations Density 0.277%

    No Known Activations