© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22369
    Prev
    Next
    INDEX
    Explanations

    Maui, Bali, Mavericks

    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
    éĥ¢
    -0.09
    ä¸Ńåħ³
    -0.08
    UserDefaults
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    ToOne
    -0.08
    ipp
    -0.08
    edly
    -0.08
    ç¢İ
    -0.08
    ét
    -0.08
    æľįåĬ¡æľºæŀĦ
    -0.08
    POSITIVE LOGITS
    ously
    0.09
    quam
    0.09
    Courtesy
    0.08
    æѤåĪ»
    0.08
    åħ¬çº¦
    0.08
    ình
    0.08
    lius
    0.08
    æ®ĩ
    0.08
    亲æĥħ
    0.08
    åij¨åĪĬ
    0.08
    Activations Density 0.004%

    No Known Activations