© 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. 51488
    Prev
    Next
    INDEX
    Explanations

    "I am" or "I want" or "I have" followed by an action

    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
    大éĻ¸
    -0.10
    å®ķ
    -0.09
    åĺĢ
    -0.09
    æ¸Į
    -0.09
    è°Ĺ
    -0.09
    æ·¡æ°´
    -0.09
    åħ¬åħ±èµĦæºIJ
    -0.09
    ä¹ĭåĨħ
    -0.09
    åĮ¹
    -0.09
    大éĻĨ
    -0.09
    POSITIVE LOGITS
    主åĬĽ
    0.08
    uya
    0.08
    .PR
    0.08
    åĨ³ä¸į
    0.08
    оÐ
    0.08
    arsing
    0.08
    .Mapping
    0.07
    éĺ²
    0.07
     пÑĢава
    0.07
    VRT
    0.07
    Activations Density 0.668%

    No Known Activations