© 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. 19138
    Prev
    Next
    INDEX
    Explanations

    initials J.E., S., E

    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
     Spartan
    -0.09
    èļľ
    -0.08
     Shack
    -0.08
    ICES
    -0.08
     Stake
    -0.08
    çŃĭ
    -0.08
    èĩ´åij½
    -0.08
    åĸ§
    -0.08
    lette
    -0.08
    ìn
    -0.08
    POSITIVE LOGITS
    çļĦä¸ľè¥¿
    0.09
     reck
    0.08
    uger
    0.08
    对èĩªå·±çļĦ
    0.08
    ç»ĵåIJĪ
    0.08
    éĽĦ
    0.08
    第ä¸ĢæŃ¥
    0.08
    ï¾ŀ
    0.08
    åIJĪä¸Ģ
    0.08
    第ä¸Ģ天
    0.08
    Activations Density 0.065%

    No Known Activations