© 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. 6883
    Prev
    Next
    INDEX
    Explanations

    that's why

    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
    çĶ±æĸ¼
    -0.10
    åĽłä¸ºä½ł
    -0.10
    æĺ¯å¦Ĥä½ķ
    -0.10
    ä¹ĭæīĢ以
    -0.09
    åĩŃä»Ģä¹Ī
    -0.09
    åħ¶å®ŀå°±æĺ¯
    -0.09
    éĤ£ä½ł
    -0.09
    èĩ³æĸ¼
    -0.09
    åĽłä¸ºæĪij
    -0.09
    æīĢæīĢéķ¿
    -0.09
    POSITIVE LOGITS
    uder
    0.10
    allas
    0.09
    rams
    0.09
    isle
    0.09
     Ost
    0.08
     Myst
    0.08
    æ¸ħæĻ°
    0.08
    hill
    0.08
     Studios
    0.08
    å°ıç¼ĸ
    0.08
    Activations Density 0.018%

    No Known Activations