© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34240
    Prev
    Next
    INDEX
    Explanations

    death of

    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
    atically
    -0.10
    ULAR
    -0.10
    åĦ¿
    -0.10
    ç«ĭãģ¦
    -0.10
    keit
    -0.09
    .ColumnHeader
    -0.09
    åĩºèº«
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    å¾Ĺä½ı
    -0.09
    ieg
    -0.09
    POSITIVE LOGITS
    ened
    0.13
    ening
    0.11
    ods
    0.10
    fully
    0.10
    ials
    0.09
    èĸĦ
    0.09
    lessness
    0.09
    less
    0.08
    çī¹åĪ«æĺ¯åľ¨
    0.08
    entic
    0.08
    Activations Density 0.029%

    No Known Activations