© 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. 21669
    Prev
    Next
    INDEX
    Explanations

    something like

    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
    ufs
    -0.09
    è¿
    -0.09
    èģĶè°Ĭ
    -0.09
     ÑĤож
    -0.08
    æ·±åħ¥å¼Ģå±ķ
    -0.08
    shi
    -0.08
    çŁ¾
    -0.08
    æĵ¦
    -0.08
    åīĶ
    -0.08
    uke
    -0.08
    POSITIVE LOGITS
    å°±åĥı
    0.22
    å¦ĤåIJĮ
    0.19
    å°±åĥıæĺ¯
    0.19
    åĥıæĺ¯
    0.19
    就好åĥı
    0.19
    类似äºİ
    0.18
     like
    0.18
    çĬ¹å¦Ĥ
    0.18
    åĥı
    0.17
    å°±å¦ĤåIJĮ
    0.16
    Activations Density 0.120%

    No Known Activations