© 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. 37172
    Prev
    Next
    INDEX
    Explanations

    trail construction

    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
    ä½łè§īå¾Ĺ
    -0.10
    éĺµå®¹
    -0.10
    é¢ĺ主
    -0.09
    åİ»è¿ĩ
    -0.09
    åĨĪ
    -0.09
    认为
    -0.09
    积累äºĨ
    -0.09
    è§īå¾Ĺ
    -0.09
    æ±²åıĸ
    -0.09
    å°±è§īå¾Ĺ
    -0.09
    POSITIVE LOGITS
    èĩªè¡Į车
    0.13
    åħ¬åĽŃ
    0.11
     park
    0.11
    åħ±äº«åįķ车
    0.11
     trail
    0.10
    åħ¨éķ¿
    0.09
    æķ£æŃ¥
    0.09
    沿线
    0.09
     walker
    0.09
    éªijè¡Į
    0.09
    Activations Density 0.053%

    No Known Activations