© 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. 33028
    Prev
    Next
    INDEX
    Explanations

    directors' names

    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
    æĮ¯åħ´
    -0.10
    é£İè²Į
    -0.10
    èľ¡
    -0.09
    åıĺå½¢
    -0.09
    èĥ¸åīį
    -0.09
    ç»į
    -0.09
    æĭ¥æĬ±
    -0.09
    ãģ¾ãģĤ
    -0.09
    æ³ķ令
    -0.09
    IR
    -0.08
    POSITIVE LOGITS
    èĻİ
    0.10
    æĪĸå¤ļ
    0.08
     drugs
    0.08
    ç£Ĭ
    0.08
    æºľ
    0.08
    åĩºæīĭ
    0.08
     dro
    0.08
    .messaging
    0.08
    ä¸įè¦ģ
    0.08
    seg
    0.07
    Activations Density 0.004%

    No Known Activations