© 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. 36449
    Prev
    Next
    INDEX
    Explanations

    escape and evasion

    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
     xúc
    -0.12
    æ´Į
    -0.09
    çŁ³æ²¹
    -0.09
    åģ¾
    -0.09
    纺
    -0.09
    æŃĩ
    -0.09
    æ´¾
    -0.09
    åĹľ
    -0.09
     ÑıзÑĭк
    -0.09
    æ»ļçIJĥ
    -0.09
    POSITIVE LOGITS
    éĢĥéģ¿
    0.23
    è§Ħéģ¿
    0.22
    躲éģ¿
    0.20
    éĢĥèĦ±
    0.19
    躲
    0.18
    éģ¿
    0.17
    éģ¿å¼Ģ
    0.17
     escape
    0.16
    éĢĥ
    0.16
    ç»ķ
    0.16
    Activations Density 0.136%

    No Known Activations