© 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. 33867
    Prev
    Next
    INDEX
    Explanations

    winning streaks or consecutive games

    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
    åĨħéĥ¨æݧåĪ¶
    -0.09
    ÙĦÙĨ
    -0.09
    é©»
    -0.09
    æ½
    -0.08
    çķ¿
    -0.08
     enclave
    -0.08
    owers
    -0.08
    åıijå±ķ壮大
    -0.08
    داÙħ
    -0.08
    erb
    -0.08
    POSITIVE LOGITS
    ä¸Ĭå²Ĺ
    0.12
    æĪ¬
    0.09
    æłī
    0.09
    æĻ®éĢļè¯Ŀ
    0.09
    anko
    0.09
     ÑĢоли
    0.08
    é¹°
    0.08
    è¿Ļä¸Ģå¹´
    0.08
    åľ¨ç¾İåĽ½
    0.08
    解éĶģ
    0.08
    Activations Density 0.009%

    No Known Activations