© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 49135
    Prev
    Next
    INDEX
    Explanations

    other organizations

    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
    éĻĤ
    -0.09
    ä¸İæĹ¶
    -0.09
    大家ä¸Ģèµ·
    -0.09
    éĤ£æ®µ
    -0.09
    éĽķ
    -0.09
    çĮĸ
    -0.08
    ayo
    -0.08
    éļıæĹ¶
    -0.08
    以便
    -0.08
    etto
    -0.08
    POSITIVE LOGITS
    主æµģ
    0.12
    ç»Ŀ大å¤ļæķ°
    0.12
    å°±è¿ŀ
    0.10
    ç»Ŀ大éĥ¨åĪĨ
    0.10
    æĶ¯æĮģ
    0.09
     backing
    0.09
    æľºæŀĦ
    0.09
    åı£å¾Ħ
    0.09
    大éĥ¨åĪĨ
    0.09
    çľĭ好
    0.09
    Activations Density 0.074%

    No Known Activations