© 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. 30472
    Prev
    Next
    INDEX
    Explanations

    most followed by superlatives

    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
    åįģè¶³
    -0.10
    满满çļĦ
    -0.10
    æĭįæĭį
    -0.10
    èĢģ人家
    -0.09
    满满
    -0.08
     alma
    -0.08
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.08
    诸
    -0.08
    åį°
    -0.08
    åĨ¤
    -0.08
    POSITIVE LOGITS
    çŁ¥åIJįçļĦ
    0.11
    æ·±å¤Ħ
    0.10
    常ç͍çļĦ
    0.10
    æł¸å¿ĥ
    0.10
    æģ°å½ĵ
    0.10
    ellan
    0.09
     ASN
    0.09
    iless
    0.09
    åĬĽè¿ĺæĺ¯
    0.09
    é¢ĨåħĪçļĦ
    0.09
    Activations Density 0.053%

    No Known Activations