© 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. 54864
    Prev
    Next
    INDEX
    Explanations

    later or future use

    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
    ä¸įè¦ģ太
    -0.10
    ç½ijåıĭè¯Ħ论
    -0.09
    åĩºæĿ¥äºĨ
    -0.09
    磧
    -0.09
    æŃ£å¸¸çļĦ
    -0.08
    ilent
    -0.08
    æįIJ
    -0.08
    éĨĴ
    -0.08
    åħ¥
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    POSITIVE LOGITS
     later
    0.12
    å°ĨæĿ¥
    0.11
     später
    0.11
    以åIJİ
    0.10
    later
    0.10
    ä¸ĩä¸Ģ
    0.10
    æĹ¥åIJİ
    0.10
    çĽį
    0.10
    ä»»ä½ķæŶåĢĻ
    0.10
     поÑĤом
    0.10
    Activations Density 0.069%

    No Known Activations