© 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. 55574
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    渺
    -0.11
    _TB
    -0.10
    åģļæ³ķ
    -0.10
    çĪ±å¿ĥ
    -0.09
    çĤ½
    -0.09
    -fashion
    -0.09
    æĺ¯è¦ģ
    -0.09
    åıĪè¦ģ
    -0.09
    çľģéĴ±
    -0.09
    åħĨ
    -0.08
    POSITIVE LOGITS
    åĸľåī§
    0.10
    ç¬ijè¯Ŀ
    0.10
     comedy
    0.10
    éĢĹ
    0.09
    çIJĨä¼ļ
    0.09
    æĭĬ
    0.09
    çĽ¸å£°
    0.09
     humor
    0.09
    åĴ¸
    0.09
     punch
    0.09
    Activations Density 0.206%

    No Known Activations