© 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. 51652
    Prev
    Next
    INDEX
    Explanations

    impersonate, shape, mimetic, marker, species

    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
    åľ®
    -0.10
    ä¸įæŃ»
    -0.09
    æ·¦
    -0.09
    ç¼ķ
    -0.09
    åı¯æĥľ
    -0.09
     carn
    -0.08
    æĥĭ
    -0.08
    é²ł
    -0.08
    dar
    -0.08
    fwrite
    -0.08
    POSITIVE LOGITS
    åĨĴ
    0.14
    伪è£ħ
    0.13
    åģĩåĨĴ
    0.13
    伪éĢł
    0.13
     Authenticate
    0.11
     mas
    0.11
     маÑģ
    0.11
     imperson
    0.10
    欺éªĹ
    0.10
     faker
    0.10
    Activations Density 0.133%

    No Known Activations