© 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. 20299
    Prev
    Next
    INDEX
    Explanations

    states of being or actions

    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
    丢
    -0.09
    abei
    -0.09
    anco
    -0.08
    ifr
    -0.08
    umer
    -0.08
    楼ä¸ĭ
    -0.08
    PB
    -0.08
     narc
    -0.08
     Tai
    -0.08
     Operation
    -0.08
    POSITIVE LOGITS
    è¿ĻéĩĮæĺ¯
    0.09
    åijĬè¯īæĪij们
    0.09
    èĮ§
    0.09
    èµ·äºĨ
    0.08
    æ¶Ī
    0.08
    åĬłä¹ĭ
    0.08
    ç´«
    0.08
    ırl
    0.08
    å±¥
    0.08
    æĤŃ
    0.08
    Activations Density 0.127%

    No Known Activations