© 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. 22766
    Prev
    Next
    INDEX
    Explanations

    ad free, your stay, our HD

    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
     Ñĩем
    -0.10
    anka
    -0.09
    åį§
    -0.09
    ç¼ł
    -0.09
    soever
    -0.09
    è°ģéĥ½
    -0.09
    ç»ıæµİæĬĢæľ¯
    -0.09
    è¥
    -0.09
    çĿ«
    -0.08
    еÑĩен
    -0.08
    POSITIVE LOGITS
    çī¹æĿĥ
    0.12
    为åħ¶
    0.11
     privileges
    0.09
    ä¾®
    0.09
    æĿ¥åĽŀ
    0.09
    带æĿ¥çļĦ
    0.09
     immensely
    0.09
     freedoms
    0.09
    çī¹æ´¾åijĺ
    0.08
    ç¾½æ¯Ľ
    0.08
    Activations Density 0.058%

    No Known Activations