© 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. 49875
    Prev
    Next
    INDEX
    Explanations

    know what

    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
    æ¸Ĭ
    -0.10
    Lint
    -0.08
    mina
    -0.08
    ä¸įæĺİ
    -0.08
    etics
    -0.08
    _ary
    -0.08
     Hurt
    -0.08
    åŁŃ
    -0.08
    å¾Īéķ¿
    -0.08
    踩
    -0.08
    POSITIVE LOGITS
    åľ¨åĵªéĩĮ
    0.10
    ä¸ĢæŦ
    0.10
    åĪ°æĿ¥
    0.10
    æīĢåľ¨
    0.10
    è§ģåĪ°
    0.09
    å°±ä¸įèĥ½
    0.09
    èī¯
    0.09
    recogn
    0.09
     recogn
    0.09
    饥饿
    0.08
    Activations Density 0.040%

    No Known Activations