© 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. 11400
    Prev
    Next
    INDEX
    Explanations

    putting together or assembling

    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
    æŃ¥
    -0.09
     indo
    -0.09
    åĹ£
    -0.08
    áŀĽ
    -0.08
    åĬ¿
    -0.08
     quo
    -0.08
     NRA
    -0.08
    elm
    -0.08
    çĹķ
    -0.08
    umes
    -0.08
    POSITIVE LOGITS
    ç»Ħè£ħ
    0.17
     ÑģбоÑĢ
    0.13
     assembly
    0.12
    ç»Ħ建
    0.12
    èµ·æĿ¥äºĨ
    0.12
    æŀĦ建
    0.11
    çŃĸåĪĴ
    0.11
    assembly
    0.11
    æŀĦéĢł
    0.11
     Assembly
    0.11
    Activations Density 0.111%

    No Known Activations