© 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. 39760
    Prev
    Next
    INDEX
    Explanations

    core data ZopeData horror Story

    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
    çķª
    -0.10
    èĥ¯
    -0.09
    åģ¥
    -0.09
    imators
    -0.09
    驼
    -0.09
    å¾µ
    -0.09
    翼
    -0.08
    èݽ
    -0.08
    éķĽ
    -0.08
    仲
    -0.08
    POSITIVE LOGITS
    éŃĦ
    0.09
    ç½ijé¦ĸ页
    0.09
    amon
    0.09
    udas
    0.09
     Soul
    0.08
    oyal
    0.08
    åIJ¹
    0.08
    ropol
    0.08
    åıĺåİĭ
    0.08
    äºī缸
    0.08
    Activations Density 0.071%

    No Known Activations