© 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. 48830
    Prev
    Next
    INDEX
    Explanations

    missile and rocket launchers

    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
    åĭĩæ°Ķ
    -0.10
    çĩİ
    -0.09
    ender
    -0.09
    æĴ¸
    -0.09
    ç»ĥ
    -0.09
    çħī
    -0.09
    æīĢåľ¨
    -0.08
    éĺ³åı°
    -0.08
    å±ħ室
    -0.08
    丰åİļ
    -0.08
    POSITIVE LOGITS
    ç«ĭãģ¦
    0.10
     Winn
    0.10
    大家
    0.09
    èĩ§
    0.08
     Earn
    0.08
     punches
    0.08
    åĵĢ
    0.08
    chio
    0.08
    LBL
    0.08
    ä¸Ĭçľĭ
    0.08
    Activations Density 0.021%

    No Known Activations