© 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. 23714
    Prev
    Next
    INDEX
    Explanations

    use ... of, end of, removed, communities in, information, growth

    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
    æī¾åĩĨ
    -0.09
    Mgr
    -0.09
     Hayden
    -0.09
    ä¸įæħİ
    -0.08
    pons
    -0.08
    éļ°
    -0.08
    _RET
    -0.08
    çŁ¥ãģ£ãģ¦
    -0.08
    Aura
    -0.08
    ä¸įéĢļ
    -0.08
    POSITIVE LOGITS
    è¿ĩå¤ļ
    0.11
    ä¸Ģè§Ĵ
    0.10
    fen
    0.10
    驹
    0.09
    太å¤ļçļĦ
    0.09
    омеÑĢ
    0.09
    迫使
    0.09
    formats
    0.09
    æī§æĦı
    0.09
     Vul
    0.09
    Activations Density 0.207%

    No Known Activations