© 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. 51104
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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
    åĪ
    -0.10
     alf
    -0.09
    åIJĮèĥŀ
    -0.09
    没åħ³ç³»
    -0.08
    大æ°Ķ
    -0.08
    éľ¹
    -0.08
     Cand
    -0.08
     Attempts
    -0.08
    åľ©
    -0.08
    è¿Ļ个éĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    æĭĪ
    0.10
    /vue
    0.10
    ä»ĸ们
    0.09
    ä¸Ģ个人
    0.09
    ä¸ĢåĢĭ人
    0.09
    OUNT
    0.09
    ount
    0.09
    çµ·
    0.09
    CRY
    0.09
    æĸ°äººçݩ家
    0.09
    Activations Density 0.044%

    No Known Activations