© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8477
    Prev
    Next
    INDEX
    Explanations

    adding "you" or "it" to questions

    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
    å¼ķãģ£
    -0.08
     ??
    -0.08
    éĵ¶æ²³
    -0.08
    /pi
    -0.08
     Pref
    -0.08
    .stub
    -0.08
    èĥ½å¤Łè®©
    -0.08
    еÑĢÑĭ
    -0.08
     Minor
    -0.08
    åIJĥå¾Ĺ
    -0.08
    POSITIVE LOGITS
    åIJ§
    0.13
    åIJĹ
    0.13
    äºĨåIJ§
    0.13
    ãĤĪãģŃ
    0.13
    åĹİ
    0.12
     nhé
    0.11
    èĭĭ
    0.11
    ãģ§ãģĻãĤĪãģŃ
    0.11
    åĺĽ
    0.11
    çĩ®
    0.10
    Activations Density 0.028%

    No Known Activations