© 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. 55986
    Prev
    Next
    INDEX
    Explanations

    forum discussion

    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
    ç½ij红
    -0.10
     Labs
    -0.09
    åĬ©çIJĨ
    -0.09
    ç½ij约
    -0.09
    iner
    -0.08
    å¶Ĥ
    -0.08
    代è¨Ģ人
    -0.08
    ghan
    -0.08
    labs
    -0.08
    (strip
    -0.08
    POSITIVE LOGITS
    讨论
    0.14
    交æµģ
    0.12
    箩
    0.11
    è°Ī论
    0.11
     discussion
    0.11
     discuss
    0.10
    åĮºåĨħ
    0.10
    çĥŃçĥĪ
    0.10
    è¨İè«ĸ
    0.10
    ä¸įç»ı
    0.10
    Activations Density 0.074%

    No Known Activations